# IETF AI/Agent Draft Landscape *Generated 2026-03-03 19:58 UTC* ## A2A protocols (85 drafts) - **[draft-guy-bary-stamp-protocol](https://datatracker.ietf.org/doc/draft-guy-bary-stamp-protocol/)** (score: 4.6) — Defines STAMP protocol for cryptographic delegation and proof in AI agent systems. Provides task-bou - **[draft-williams-netmod-lm-hierarchy-topology](https://datatracker.ietf.org/doc/draft-williams-netmod-lm-hierarchy-topology/)** (score: 4.6) — Defines YANG data model for hierarchical language model coordination across tiny, small, and large L - **[draft-chang-agent-token-efficient](https://datatracker.ietf.org/doc/draft-chang-agent-token-efficient/)** (score: 4.5) — Defines ADOL (Agentic Data Optimization Layer) to address token bloat in agent communication protoco - **[draft-chen-oauth-rar-agent-extensions](https://datatracker.ietf.org/doc/draft-chen-oauth-rar-agent-extensions/)** (score: 4.2) — Extends OAuth RAR with policy_context and lifecycle_binding members for AI agent environments. Enabl - **[draft-mallick-muacp](https://datatracker.ietf.org/doc/draft-mallick-muacp/)** (score: 4.2) — Resource-efficient messaging protocol specifically designed for constrained IoT/Edge devices with de - **[draft-li-spring-rdma-multicast-over-srv6](https://datatracker.ietf.org/doc/draft-li-spring-rdma-multicast-over-srv6/)** (score: 4.2) — Specifies SRv6 extensions for RDMA multicast delivery with new End.MT behavior and ACK/NACK aggregat - **[draft-song-tsvwg-camp](https://datatracker.ietf.org/doc/draft-song-tsvwg-camp/)** (score: 4.2) — Proposes CAMP, a multipath transport protocol for interactive multimodal LLM systems that maintains - **[draft-narajala-ans](https://datatracker.ietf.org/doc/draft-narajala-ans/)** (score: 4.2) — Introduces Agent Name Service (ANS) as a DNS-based universal directory for AI agent discovery and ve - **[draft-oauth-transaction-tokens-for-agents](https://datatracker.ietf.org/doc/draft-oauth-transaction-tokens-for-agents/)** (score: 4.2) — Extends OAuth Transaction Tokens framework to support agent context propagation with actor and princ - **[draft-zhang-dmsc-mas-communication](https://datatracker.ietf.org/doc/draft-zhang-dmsc-mas-communication/)** (score: 4.2) — Analyzes security risks in multi-agent communication and limitations of existing protocols like TLS - **[draft-li-dmsc-macp](https://datatracker.ietf.org/doc/draft-li-dmsc-macp/)** (score: 4.2) — Specifies a comprehensive multi-agent collaboration protocol suite using Agent Gateways for registra - **[draft-yue-anima-agent-recovery-networks](https://datatracker.ietf.org/doc/draft-yue-anima-agent-recovery-networks/)** (score: 4.1) — Defines task-oriented multi-agent framework for fault recovery in converged mobile networks. Targets - **[draft-nederveld-adl](https://datatracker.ietf.org/doc/draft-nederveld-adl/)** (score: 4.1) — Defines ADL, a JSON-based standard for describing AI agents including their capabilities, tools, per - **[draft-mw-spice-actor-chain](https://datatracker.ietf.org/doc/draft-mw-spice-actor-chain/)** (score: 4.1) — Extends OAuth 2.0 Token Exchange with cryptographically verifiable actor chains to provide tamper-ev - **[draft-jadoon-nmrg-agentic-ai-autonomous-networks](https://datatracker.ietf.org/doc/draft-jadoon-nmrg-agentic-ai-autonomous-networks/)** (score: 4.1) — Introduces architectural principles for integrating AI agents into IP protocol stack layers while pr - **[draft-ietf-lisp-nexagon](https://datatracker.ietf.org/doc/draft-ietf-lisp-nexagon/)** (score: 4.0) — Combines LISP with H3 spatial indexing to create geospatial intelligence network for physical-world - **[draft-barney-caam](https://datatracker.ietf.org/doc/draft-barney-caam/)** (score: 4.0) — Specifies Contextual Agent Authorization Mesh for runtime authorization of agents after discovery, p - **[draft-nennemann-wimse-ect](https://datatracker.ietf.org/doc/draft-nennemann-wimse-ect/)** (score: 4.0) — Defines Execution Context Tokens as JWT extension to WIMSE for tracking task execution in distribute - **[draft-jennings-ai-mcp-over-moq](https://datatracker.ietf.org/doc/draft-jennings-ai-mcp-over-moq/)** (score: 4.0) — Defines how to transport Model Context Protocol (MCP) messages over Media over QUIC Transport (MOQT) - **[draft-han-anima-ai-asa](https://datatracker.ietf.org/doc/draft-han-anima-ai-asa/)** (score: 4.0) — Analyzes the impact of enhancing ANIMA's Autonomic Service Agents with AI/LLM capabilities, focusing - **[draft-liao-aipref-autoctl-core](https://datatracker.ietf.org/doc/draft-liao-aipref-autoctl-core/)** (score: 4.0) — Defines core machine-readable protocol for server-side automation permissions targeting AI-driven we - **[draft-ainp-protocol](https://datatracker.ietf.org/doc/draft-ainp-protocol/)** (score: 3.9) — Defines semantic communication protocol for AI agents using intent-based routing and negotiation. Re - **[draft-agent-gw](https://datatracker.ietf.org/doc/draft-agent-gw/)** (score: 3.9) — Proposes an Intelligent Agent Communication Gateway for large-scale multi-agent collaboration. Featu - **[draft-mp-agntcy-ads](https://datatracker.ietf.org/doc/draft-mp-agntcy-ads/)** (score: 3.9) — Describes Agent Directory Service for storing and discovering AI agent metadata based on skills. Fea - **[draft-rosenberg-aiproto-cheq](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-cheq/)** (score: 3.9) — Proposes CHEQ protocol for human confirmation of AI agent decisions before execution. Protects again - **[draft-zeng-opsawg-llm-netconf-gap](https://datatracker.ietf.org/doc/draft-zeng-opsawg-llm-netconf-gap/)** (score: 3.9) — Analyzes gaps in existing network configuration protocols for LLM-driven intent-based networking. Id - **[draft-akhavain-moussa-ai-network](https://datatracker.ietf.org/doc/draft-akhavain-moussa-ai-network/)** (score: 3.9) — Proposes Data and Agent Aware-Inference and Training Network (DA-ITN) architecture. Comprehensive mu - **[draft-rosenberg-aiproto-a2t](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-a2t/)** (score: 3.9) — Defines Agent-to-Tool (A2T) protocol for integrating third-party APIs into AI agent operations. Prov - **[draft-cui-ai-agent-discovery-invocation](https://datatracker.ietf.org/doc/draft-cui-ai-agent-discovery-invocation/)** (score: 3.9) — Proposes standardized protocol for AI agent discovery and invocation with common metadata format and - **[draft-ravikiran-clawdentity-protocol](https://datatracker.ietf.org/doc/draft-ravikiran-clawdentity-protocol/)** (score: 3.9) — Specifies Clawdentity protocol for cryptographic identity and trust in AI agent communication. Provi - **[draft-jurkovikj-httpapi-agentic-state](https://datatracker.ietf.org/doc/draft-jurkovikj-httpapi-agentic-state/)** (score: 3.9) — Defines Agentic State Transfer (AST) HTTP profile for managing canonical resource state across multi - **[draft-tejido-swp-core](https://datatracker.ietf.org/doc/draft-tejido-swp-core/)** (score: 3.9) — Specifies SlimWire Protocol Core, a binary framing layer for agent/tool messaging with profile-based - **[draft-templin-intarea-aero2](https://datatracker.ietf.org/doc/draft-templin-intarea-aero2/)** (score: 3.9) — Specifies AERO service for IP internetworking over overlay multilink networks using IPv6 ND for cont - **[draft-ramadan-mboned-sonar](https://datatracker.ietf.org/doc/draft-ramadan-mboned-sonar/)** (score: 3.8) — Specifies a protocol for verifiable multicast delivery using cryptoeconomic accountability and stati - **[draft-luan-rtgwg-sdaf](https://datatracker.ietf.org/doc/draft-luan-rtgwg-sdaf/)** (score: 3.8) — Proposes symmetry-driven forwarding mechanism for LEO satellite networks to avoid routing loops and - **[draft-zhao-nmop-network-management-agent](https://datatracker.ietf.org/doc/draft-zhao-nmop-network-management-agent/)** (score: 3.8) — Defines AI-driven Network Management Agent concept for Level 4 autonomous networks. Specifies integr - **[draft-eckert-anima-acp-free-ani](https://datatracker.ietf.org/doc/draft-eckert-anima-acp-free-ani/)** (score: 3.8) — Describes lightweight variation of Autonomic Networking Infrastructure without expensive ACP impleme - **[draft-li-individual-inip](https://datatracker.ietf.org/doc/draft-li-individual-inip/)** (score: 3.8) — Specifies a protocol for performing lightweight ML inference directly in network devices like switch - **[draft-ietf-aipref-attach](https://datatracker.ietf.org/doc/draft-ietf-aipref-attach/)** (score: 3.8) — Specifies how AI usage preferences can be signaled during HTTP content acquisition. Updates RFC 9309 - **[draft-rosenberg-aiproto-framework](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-framework/)** (score: 3.7) — Provides framework and requirements for AI agent protocols on the Internet. Surveys existing approac - **[draft-an-nmrg-i2icf-cits](https://datatracker.ietf.org/doc/draft-an-nmrg-i2icf-cits/)** (score: 3.7) — Defines framework for orchestrating In-Network Computing Functions in Cooperative Intelligent Transp - **[draft-melnikov-sasl2](https://datatracker.ietf.org/doc/draft-melnikov-sasl2/)** (score: 3.7) — Updates SASL framework to support modern authentication requirements including multi-factor authenti - **[draft-howe-sipcore-mcp-extension](https://datatracker.ietf.org/doc/draft-howe-sipcore-mcp-extension/)** (score: 3.7) — Defines SIP extension to carry Model Context Protocol with new option-tags, headers, and media types - **[draft-sogomonian-aiip-architecture](https://datatracker.ietf.org/doc/draft-sogomonian-aiip-architecture/)** (score: 3.7) — Defines architectural model for Artificial Intelligence Internet Protocol (AIIP) enabling stateless, - **[draft-rosenberg-aiproto](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto/)** (score: 3.7) — Defines N-ACT protocol for AI agents to discover and invoke third-party tools and APIs. Focuses on e - **[draft-rosenberg-aiproto-nact](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-nact/)** (score: 3.7) — Defines N-ACT protocol for AI agents to discover and invoke third-party tools and APIs. Focuses on e - **[draft-pocero-authkem-edhoc](https://datatracker.ietf.org/doc/draft-pocero-authkem-edhoc/)** (score: 3.7) — Extends EDHOC with KEM-based authentication for post-quantum resistance. Enables signature-free quan - **[draft-zyyhl-agent-networks-framework](https://datatracker.ietf.org/doc/draft-zyyhl-agent-networks-framework/)** (score: 3.6) — Defines comprehensive framework for AI agent networks based on Agent Network Protocol (ANP). Provide - **[draft-kotecha-agentic-dispute-protocol](https://datatracker.ietf.org/doc/draft-kotecha-agentic-dispute-protocol/)** (score: 3.6) — Defines a protocol for autonomous agents to file and resolve disputes through structured automated p - **[draft-mao-rtgwg-agent-comm-protocol-gap-analysis](https://datatracker.ietf.org/doc/draft-mao-rtgwg-agent-comm-protocol-gap-analysis/)** (score: 3.6) — Analyzes gaps in existing networking and AI protocols for cross-device communication between AI agen - **[draft-zlgsgl-rtgwg-agents-networking-framework](https://datatracker.ietf.org/doc/draft-zlgsgl-rtgwg-agents-networking-framework/)** (score: 3.6) — Introduces a comprehensive agents networking framework for enterprise and broadband environments. De - **[draft-han-rtgwg-agent-gateway-intercomm-framework](https://datatracker.ietf.org/doc/draft-han-rtgwg-agent-gateway-intercomm-framework/)** (score: 3.6) — Defines framework for intercommunication between Agent Gateways in Agent Internet ecosystem. Address - **[draft-yang-ioa-protocol](https://datatracker.ietf.org/doc/draft-yang-ioa-protocol/)** (score: 3.6) — Defines the Internet of Agents Protocol for distributed collaboration among heterogeneous AI agents. - **[draft-rosenberg-cheq](https://datatracker.ietf.org/doc/draft-rosenberg-cheq/)** (score: 3.6) — Proposes CHEQ protocol for human-in-the-loop confirmation of AI agent decisions before execution. Us - **[draft-mozleywilliams-dnsop-bandaid](https://datatracker.ietf.org/doc/draft-mozleywilliams-dnsop-bandaid/)** (score: 3.6) — Proposes using DNS with SVCB records to enable AI agent discovery and capability advertisement. Leve - **[draft-li-semantic-routing-architecture](https://datatracker.ietf.org/doc/draft-li-semantic-routing-architecture/)** (score: 3.6) — Introduces semantic routing architecture using intent vectors and trust scores for AI agent communic - **[draft-vandoulas-aidp](https://datatracker.ietf.org/doc/draft-vandoulas-aidp/)** (score: 3.6) — Defines a comprehensive control-plane protocol for secure agent interactions with delegation, author - **[draft-altanai-aipref-realtime-protocol-bindings](https://datatracker.ietf.org/doc/draft-altanai-aipref-realtime-protocol-bindings/)** (score: 3.6) — Defines how AI preference expressions are bound to real-time protocols like SIP and SDP. Specifies h - **[draft-ietf-ace-edhoc-oscore-profile](https://datatracker.ietf.org/doc/draft-ietf-ace-edhoc-oscore-profile/)** (score: 3.6) — Defines ACE framework profile using EDHOC for mutual authentication and OSCORE for secure communicat - **[draft-liu-oauth-a2a-profile](https://datatracker.ietf.org/doc/draft-liu-oauth-a2a-profile/)** (score: 3.6) — Specifies OAuth Transaction Token profile for Agent-to-Agent communication. Embeds call chain contex - **[draft-templin-6man-aero3](https://datatracker.ietf.org/doc/draft-templin-6man-aero3/)** (score: 3.6) — Specifies automatic extended route optimization for IP internetworking over overlay multilink networ - **[draft-liu-dmsc-acps-arc](https://datatracker.ietf.org/doc/draft-liu-dmsc-acps-arc/)** (score: 3.6) — Proposes Agent Collaboration Protocols architecture for Internet of Agents, covering agent lifecycle - **[draft-liang-agentdns](https://datatracker.ietf.org/doc/draft-liang-agentdns/)** (score: 3.5) — Proposes a DNS-inspired naming and service discovery system for LLM agents to enable autonomous disc - **[draft-song-oauth-ai-agent-collaborate-authz](https://datatracker.ietf.org/doc/draft-song-oauth-ai-agent-collaborate-authz/)** (score: 3.5) — Proposes OAuth 2.0 extension for multi-AI agent collaboration with applier-on-behalf-of authorizatio - **[draft-mozley-aidiscovery](https://datatracker.ietf.org/doc/draft-mozley-aidiscovery/)** (score: 3.5) — Defines requirements and considerations for AI agent-to-agent discovery mechanisms. Addresses the fu - **[draft-wang-hjs-accountability](https://datatracker.ietf.org/doc/draft-wang-hjs-accountability/)** (score: 3.5) — Defines HJS accountability layer for AI agents using blockchain-anchored timestamps to create immuta - **[draft-meta-layer-overview](https://datatracker.ietf.org/doc/draft-meta-layer-overview/)** (score: 3.5) — Introduces Meta-layer concept as coordination substrate for presence, annotation, and governance on - **[draft-zhang-rvp-problem-statement](https://datatracker.ietf.org/doc/draft-zhang-rvp-problem-statement/)** (score: 3.5) — Proposes Real-Virtual Agent Protocol for coordinating physical entities with digital agents through - **[draft-zeng-opsawg-applicability-mcp-a2a](https://datatracker.ietf.org/doc/draft-zeng-opsawg-applicability-mcp-a2a/)** (score: 3.5) — Analyzes NETCONF limitations for advanced scenarios and proposes MCP and A2A protocols as complement - **[draft-li-dmsc-mcps-agw](https://datatracker.ietf.org/doc/draft-li-dmsc-mcps-agw/)** (score: 3.5) — Defines a protocol suite using Agent Gateways as control-plane entities for multi-agent collaboratio - **[draft-jiang-seat-dynamic-attestation](https://datatracker.ietf.org/doc/draft-jiang-seat-dynamic-attestation/)** (score: 3.4) — Defines dynamic attestation mechanisms for AI agents to convey runtime posture changes during long-l - **[draft-romanchuk-normative-admissibility](https://datatracker.ietf.org/doc/draft-romanchuk-normative-admissibility/)** (score: 3.4) — Establishes a framework for evaluating whether autonomous agent speech acts are admissible based on - **[draft-du-catalist-routing-considerations](https://datatracker.ietf.org/doc/draft-du-catalist-routing-considerations/)** (score: 3.4) — Proposes routing considerations for AI agent-to-agent communication in overlay networks. Focuses on - **[draft-kartha-internet20-ainative](https://datatracker.ietf.org/doc/draft-kartha-internet20-ainative/)** (score: 3.4) — Proposes Internet 2.0 architecture with AI models as first-class network entities, including HTTP+AI - **[draft-yan-a2a-device-agent-applicability](https://datatracker.ietf.org/doc/draft-yan-a2a-device-agent-applicability/)** (score: 3.4) — Discusses applying Agent-to-Agent (A2A) Protocol to network management for communication between Con - **[draft-zw-rtgwg-mcp-network-mgmt](https://datatracker.ietf.org/doc/draft-zw-rtgwg-mcp-network-mgmt/)** (score: 3.4) — Specifies MCP extensions for network equipment management with routers/switches as MCP servers. Defi - **[draft-stephan-ai-agent-6g](https://datatracker.ietf.org/doc/draft-stephan-ai-agent-6g/)** (score: 3.4) — Examines AI agent communication protocols specifically for 6G systems based on 3GPP requirements. Ex - **[draft-cosmos-protocol-specification](https://datatracker.ietf.org/doc/draft-cosmos-protocol-specification/)** (score: 3.3) — Defines comprehensive badge-based identity and communication system with trust scoring, post-quantum - **[draft-sz-dmsc-iaip](https://datatracker.ietf.org/doc/draft-sz-dmsc-iaip/)** (score: 3.3) — Defines Intent-based Agent Interconnection Protocol (IAIP) for dynamic agent discovery and routing a - **[draft-wang-cats-innetwork-infer](https://datatracker.ietf.org/doc/draft-wang-cats-innetwork-infer/)** (score: 3.3) — Proposes a framework for decentralized LLM inference across untrusted participants using layer-aware - **[draft-mcp-over-moqt](https://datatracker.ietf.org/doc/draft-mcp-over-moqt/)** (score: 3.3) — Defines transport mapping for Model Context Protocol over Media over QUIC Transport. Specifies how M - **[draft-jennings-mcp-over-moqt](https://datatracker.ietf.org/doc/draft-jennings-mcp-over-moqt/)** (score: 3.3) — Defines transport mapping for Model Context Protocol over Media over QUIC Transport. Specifies how M - **[draft-liu-rtgwg-agent-gateway-requirements](https://datatracker.ietf.org/doc/draft-liu-rtgwg-agent-gateway-requirements/)** (score: 3.2) — Discusses requirements for Agent Gateways in agent-to-agent communications to improve scalability, e - **[draft-pioli-agent-discovery](https://datatracker.ietf.org/doc/draft-pioli-agent-discovery/)** (score: 3.2) — Specifies ARDP, a lightweight protocol for agent registration and discovery in distributed environme - **[draft-gaikwad-woa](https://datatracker.ietf.org/doc/draft-gaikwad-woa/)** (score: 3.2) — Specifies Web of Agents (WoA) format using JSON Schema to describe AI agent inputs/outputs served fr ## AI safety / guardrails / alignment (1 drafts) - **[draft-chen-agent-decoupled-authorization-model](https://datatracker.ietf.org/doc/draft-chen-agent-decoupled-authorization-model/)** (score: 3.5) — This draft proposes a decoupled authorization framework for AI agents that enables dynamic, intent-b ## AI safety/alignment (35 drafts) - **[draft-cowles-volt](https://datatracker.ietf.org/doc/draft-cowles-volt/)** (score: 4.8) — Defines tamper-evident execution trace format for AI agent workflows using hash chains and cryptogra - **[draft-aylward-daap-v2](https://datatracker.ietf.org/doc/draft-aylward-daap-v2/)** (score: 4.8) — Defines comprehensive protocol for AI agent accountability including authentication, monitoring, and - **[draft-guy-bary-stamp-protocol](https://datatracker.ietf.org/doc/draft-guy-bary-stamp-protocol/)** (score: 4.6) — Defines STAMP protocol for cryptographic delegation and proof in AI agent systems. Provides task-bou - **[draft-drake-email-tpm-attestation](https://datatracker.ietf.org/doc/draft-drake-email-tpm-attestation/)** (score: 4.6) — Defines hardware attestation for email using TPM verification chains to prevent spam and provide Syb - **[draft-goswami-agentic-jwt](https://datatracker.ietf.org/doc/draft-goswami-agentic-jwt/)** (score: 4.5) — Extends OAuth 2.0 with Agentic JWT to address authorization challenges in autonomous AI systems. Int - **[draft-birkholz-verifiable-agent-conversations](https://datatracker.ietf.org/doc/draft-birkholz-verifiable-agent-conversations/)** (score: 4.5) — Defines CDDL-based data format for verifiable agent conversation records using COSE signing. Support - **[draft-aylward-aiga-2](https://datatracker.ietf.org/doc/draft-aylward-aiga-2/)** (score: 4.5) — Comprehensive AI governance framework with tiered risk model, federated authority network, and econo - **[draft-mw-wimse-transitive-attestation](https://datatracker.ietf.org/doc/draft-mw-wimse-transitive-attestation/)** (score: 4.3) — Defines WIMSE profile for cryptographically binding workload identities to their execution environme - **[draft-aylward-aiga-1](https://datatracker.ietf.org/doc/draft-aylward-aiga-1/)** (score: 4.2) — Specifies AI Governance and Accountability Protocol with tiered risk-based governance model. Include - **[draft-aap-oauth-profile](https://datatracker.ietf.org/doc/draft-aap-oauth-profile/)** (score: 4.2) — Defines an OAuth 2.0 authorization profile specifically for autonomous AI agents, extending existing - **[draft-zhang-dmsc-mas-communication](https://datatracker.ietf.org/doc/draft-zhang-dmsc-mas-communication/)** (score: 4.2) — Analyzes security risks in multi-agent communication and limitations of existing protocols like TLS - **[draft-jewell-aibdp](https://datatracker.ietf.org/doc/draft-jewell-aibdp/)** (score: 4.2) — Defines AI Boundary Declaration Protocol for expressing content usage boundaries for AI systems. Pro - **[draft-liu-agent-operation-authorization](https://datatracker.ietf.org/doc/draft-liu-agent-operation-authorization/)** (score: 4.1) — Specifies framework for verifiable delegation of actions from humans to AI agents using JWT tokens. - **[draft-cui-nmrg-llm-nm](https://datatracker.ietf.org/doc/draft-cui-nmrg-llm-nm/)** (score: 4.1) — Defines framework for collaborative network management between LLM agents and human operators. Intro - **[draft-schulze-ecap](https://datatracker.ietf.org/doc/draft-schulze-ecap/)** (score: 4.1) — ECAP defines a cryptographically-verified protocol for web crawlers to obtain consent from hosts bef - **[draft-mw-spice-actor-chain](https://datatracker.ietf.org/doc/draft-mw-spice-actor-chain/)** (score: 4.1) — Extends OAuth 2.0 Token Exchange with cryptographically verifiable actor chains to provide tamper-ev - **[draft-barney-caam](https://datatracker.ietf.org/doc/draft-barney-caam/)** (score: 4.0) — Specifies Contextual Agent Authorization Mesh for runtime authorization of agents after discovery, p - **[draft-han-anima-ai-asa](https://datatracker.ietf.org/doc/draft-han-anima-ai-asa/)** (score: 4.0) — Analyzes the impact of enhancing ANIMA's Autonomic Service Agents with AI/LLM capabilities, focusing - **[draft-rosenberg-aiproto-cheq](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-cheq/)** (score: 3.9) — Proposes CHEQ protocol for human confirmation of AI agent decisions before execution. Protects again - **[draft-berlinai-vera](https://datatracker.ietf.org/doc/draft-berlinai-vera/)** (score: 3.9) — Introduces VERA, a zero-trust architecture for AI agent security with five enforcement pillars and c - **[draft-chen-ai-agent-auth-new-requirements](https://datatracker.ietf.org/doc/draft-chen-ai-agent-auth-new-requirements/)** (score: 3.8) — Identifies new authentication and authorization requirements for AI agents that go beyond traditiona - **[draft-ni-a2a-ai-agent-security-requirements](https://datatracker.ietf.org/doc/draft-ni-a2a-ai-agent-security-requirements/)** (score: 3.7) — Establishes security requirements for AI agents across their operational lifecycle. Covers provision - **[draft-kotecha-agentic-dispute-protocol](https://datatracker.ietf.org/doc/draft-kotecha-agentic-dispute-protocol/)** (score: 3.6) — Defines a protocol for autonomous agents to file and resolve disputes through structured automated p - **[draft-rosenberg-oauth-aauth](https://datatracker.ietf.org/doc/draft-rosenberg-oauth-aauth/)** (score: 3.6) — Extends OAuth 2.1 for AI agents operating through PSTN/SMS channels to obtain access tokens using PI - **[draft-rosenberg-cheq](https://datatracker.ietf.org/doc/draft-rosenberg-cheq/)** (score: 3.6) — Proposes CHEQ protocol for human-in-the-loop confirmation of AI agent decisions before execution. Us - **[draft-messous-eat-ai](https://datatracker.ietf.org/doc/draft-messous-eat-ai/)** (score: 3.6) — Defines an Entity Attestation Token profile for remote attestation of autonomous AI agents, specifyi - **[draft-reilly-sentinel-protocol](https://datatracker.ietf.org/doc/draft-reilly-sentinel-protocol/)** (score: 3.6) — Defines blockchain-anchored integrity protocol for AI lifecycle provenance using Sentinel Evidence P - **[draft-vaughan-aipref-vocab](https://datatracker.ietf.org/doc/draft-vaughan-aipref-vocab/)** (score: 3.6) — Proposes vocabulary for rightsholders to express content preferences for AI training use through met - **[draft-wang-hjs-accountability](https://datatracker.ietf.org/doc/draft-wang-hjs-accountability/)** (score: 3.5) — Defines HJS accountability layer for AI agents using blockchain-anchored timestamps to create immuta - **[draft-ietf-sml-trust](https://datatracker.ietf.org/doc/draft-ietf-sml-trust/)** (score: 3.5) — Provides trust and security recommendations for handling structured data in email messages. Addresse - **[draft-yuan-rtgwg-security-agent-usecase](https://datatracker.ietf.org/doc/draft-yuan-rtgwg-security-agent-usecase/)** (score: 3.4) — Proposes AI Network Security Agents for routers to provide intelligent, adaptive security capabiliti - **[draft-huang-rats-agentic-eat-cap-attest](https://datatracker.ietf.org/doc/draft-huang-rats-agentic-eat-cap-attest/)** (score: 3.4) — Extends Entity Attestation Token (EAT) to support capability attestation for agentic AI systems. Ena - **[draft-jiang-seat-dynamic-attestation](https://datatracker.ietf.org/doc/draft-jiang-seat-dynamic-attestation/)** (score: 3.4) — Defines dynamic attestation mechanisms for AI agents to convey runtime posture changes during long-l - **[draft-romanchuk-normative-admissibility](https://datatracker.ietf.org/doc/draft-romanchuk-normative-admissibility/)** (score: 3.4) — Establishes a framework for evaluating whether autonomous agent speech acts are admissible based on - **[draft-diaconu-agents-authz-info-sharing](https://datatracker.ietf.org/doc/draft-diaconu-agents-authz-info-sharing/)** (score: 3.2) — Addresses authorization challenges in distributed multi-agent systems across multiple domains. Cover ## Agent discovery / registration (5 drafts) - **[draft-nandakumar-agent-sd-jwt](https://datatracker.ietf.org/doc/draft-nandakumar-agent-sd-jwt/)** (score: 3.9) — This draft defines SD-Card, a Selective Disclosure JWT encoding of Agent Cards that enables privacy- - **[draft-wahl-scim-agent-schema](https://datatracker.ietf.org/doc/draft-wahl-scim-agent-schema/)** (score: 3.9) — This draft extends the SCIM (System for Cross-domain Identity Management) protocol to support AI age - **[draft-huang-acme-scalable-agent-enrollment](https://datatracker.ietf.org/doc/draft-huang-acme-scalable-agent-enrollment/)** (score: 3.5) — This draft proposes two scalable models for certificate enrollment of AI agents: one using Zero-Know - **[draft-zheng-dispatch-agent-identity-management](https://datatracker.ietf.org/doc/draft-zheng-dispatch-agent-identity-management/)** (score: 3.3) — This draft proposes an identity management framework for agents in an Internet of Agents (IOA) syste - **[draft-narvaneni-agent-uri](https://datatracker.ietf.org/doc/draft-narvaneni-agent-uri/)** (score: 3.3) — This draft defines the agent:// URI scheme for addressing and interoperating with software agents ac ## Agent discovery/reg (43 drafts) - **[draft-narajala-ans](https://datatracker.ietf.org/doc/draft-narajala-ans/)** (score: 4.2) — Introduces Agent Name Service (ANS) as a DNS-based universal directory for AI agent discovery and ve - **[draft-li-dmsc-macp](https://datatracker.ietf.org/doc/draft-li-dmsc-macp/)** (score: 4.2) — Specifies a comprehensive multi-agent collaboration protocol suite using Agent Gateways for registra - **[draft-cui-dns-native-agent-naming-resolution](https://datatracker.ietf.org/doc/draft-cui-dns-native-agent-naming-resolution/)** (score: 4.1) — Specifies DNS-native naming and resolution for AI agents using FQDNs and SVCB records. Emphasizes DN - **[draft-nederveld-adl](https://datatracker.ietf.org/doc/draft-nederveld-adl/)** (score: 4.1) — Defines ADL, a JSON-based standard for describing AI agents including their capabilities, tools, per - **[draft-ainp-protocol](https://datatracker.ietf.org/doc/draft-ainp-protocol/)** (score: 3.9) — Defines semantic communication protocol for AI agents using intent-based routing and negotiation. Re - **[draft-ietf-lake-authz](https://datatracker.ietf.org/doc/draft-ietf-lake-authz/)** (score: 3.9) — Specifies lightweight authorization using EDHOC for zero-touch device onboarding. Enables secure enr - **[draft-agent-gw](https://datatracker.ietf.org/doc/draft-agent-gw/)** (score: 3.9) — Proposes an Intelligent Agent Communication Gateway for large-scale multi-agent collaboration. Featu - **[draft-mp-agntcy-ads](https://datatracker.ietf.org/doc/draft-mp-agntcy-ads/)** (score: 3.9) — Describes Agent Directory Service for storing and discovering AI agent metadata based on skills. Fea - **[draft-rosenberg-aiproto-a2t](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-a2t/)** (score: 3.9) — Defines Agent-to-Tool (A2T) protocol for integrating third-party APIs into AI agent operations. Prov - **[draft-cui-ai-agent-discovery-invocation](https://datatracker.ietf.org/doc/draft-cui-ai-agent-discovery-invocation/)** (score: 3.9) — Proposes standardized protocol for AI agent discovery and invocation with common metadata format and - **[draft-sogomonian-ai-uri-scheme](https://datatracker.ietf.org/doc/draft-sogomonian-ai-uri-scheme/)** (score: 3.8) — Defines experimental AI URI scheme for dedicated AI resource access. Enables native connectivity for - **[draft-abbey-scim-agent-extension](https://datatracker.ietf.org/doc/draft-abbey-scim-agent-extension/)** (score: 3.8) — Extends SCIM 2.0 protocol to manage AI agents and agentic applications across domains. Adds new sche - **[draft-eckert-anima-acp-free-ani](https://datatracker.ietf.org/doc/draft-eckert-anima-acp-free-ani/)** (score: 3.8) — Describes lightweight variation of Autonomic Networking Infrastructure without expensive ACP impleme - **[draft-zheng-agent-identity-management](https://datatracker.ietf.org/doc/draft-zheng-agent-identity-management/)** (score: 3.7) — Defines comprehensive agent identity management for Internet of Agents systems. Covers agent registr - **[draft-an-nmrg-i2icf-cits](https://datatracker.ietf.org/doc/draft-an-nmrg-i2icf-cits/)** (score: 3.7) — Defines framework for orchestrating In-Network Computing Functions in Cooperative Intelligent Transp - **[draft-howe-sipcore-mcp-extension](https://datatracker.ietf.org/doc/draft-howe-sipcore-mcp-extension/)** (score: 3.7) — Defines SIP extension to carry Model Context Protocol with new option-tags, headers, and media types - **[draft-rosenberg-aiproto](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto/)** (score: 3.7) — Defines N-ACT protocol for AI agents to discover and invoke third-party tools and APIs. Focuses on e - **[draft-rosenberg-aiproto-nact](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-nact/)** (score: 3.7) — Defines N-ACT protocol for AI agents to discover and invoke third-party tools and APIs. Focuses on e - **[draft-zyyhl-agent-networks-framework](https://datatracker.ietf.org/doc/draft-zyyhl-agent-networks-framework/)** (score: 3.6) — Defines comprehensive framework for AI agent networks based on Agent Network Protocol (ANP). Provide - **[draft-zlgsgl-rtgwg-agents-networking-framework](https://datatracker.ietf.org/doc/draft-zlgsgl-rtgwg-agents-networking-framework/)** (score: 3.6) — Introduces a comprehensive agents networking framework for enterprise and broadband environments. De - **[draft-han-rtgwg-agent-gateway-intercomm-framework](https://datatracker.ietf.org/doc/draft-han-rtgwg-agent-gateway-intercomm-framework/)** (score: 3.6) — Defines framework for intercommunication between Agent Gateways in Agent Internet ecosystem. Address - **[draft-yang-ioa-protocol](https://datatracker.ietf.org/doc/draft-yang-ioa-protocol/)** (score: 3.6) — Defines the Internet of Agents Protocol for distributed collaboration among heterogeneous AI agents. - **[draft-mozleywilliams-dnsop-bandaid](https://datatracker.ietf.org/doc/draft-mozleywilliams-dnsop-bandaid/)** (score: 3.6) — Proposes using DNS with SVCB records to enable AI agent discovery and capability advertisement. Leve - **[draft-li-semantic-routing-architecture](https://datatracker.ietf.org/doc/draft-li-semantic-routing-architecture/)** (score: 3.6) — Introduces semantic routing architecture using intent vectors and trust scores for AI agent communic - **[draft-mozleywilliams-dnsop-dnsaid](https://datatracker.ietf.org/doc/draft-mozleywilliams-dnsop-dnsaid/)** (score: 3.6) — Uses existing DNS infrastructure for AI agent discovery through structured namespace and metadata ex - **[draft-eggert-mailmaint-uaautoconf](https://datatracker.ietf.org/doc/draft-eggert-mailmaint-uaautoconf/)** (score: 3.6) — Specifies automatic configuration mechanism for email, calendar, and contact applications. Enables s - **[draft-li-cats-idn](https://datatracker.ietf.org/doc/draft-li-cats-idn/)** (score: 3.6) — Introduces Intelligence Delivery Network (IDN) framework for deploying ML models across distributed - **[draft-liu-dmsc-acps-arc](https://datatracker.ietf.org/doc/draft-liu-dmsc-acps-arc/)** (score: 3.6) — Proposes Agent Collaboration Protocols architecture for Internet of Agents, covering agent lifecycle - **[draft-liang-agentdns](https://datatracker.ietf.org/doc/draft-liang-agentdns/)** (score: 3.5) — Proposes a DNS-inspired naming and service discovery system for LLM agents to enable autonomous disc - **[draft-mozley-aidiscovery](https://datatracker.ietf.org/doc/draft-mozley-aidiscovery/)** (score: 3.5) — Defines requirements and considerations for AI agent-to-agent discovery mechanisms. Addresses the fu - **[draft-ye-problems-and-requirements-of-dns-for-ioa](https://datatracker.ietf.org/doc/draft-ye-problems-and-requirements-of-dns-for-ioa/)** (score: 3.5) — Analyzes DNS challenges for Internet of Agents scenarios and identifies technical requirements. Expl - **[draft-li-dmsc-mcps-agw](https://datatracker.ietf.org/doc/draft-li-dmsc-mcps-agw/)** (score: 3.5) — Defines a protocol suite using Agent Gateways as control-plane entities for multi-agent collaboratio - **[draft-kartha-grd](https://datatracker.ietf.org/doc/draft-kartha-grd/)** (score: 3.4) — Defines architectural framework for discovering network resources based on physical location and con - **[draft-du-catalist-routing-considerations](https://datatracker.ietf.org/doc/draft-du-catalist-routing-considerations/)** (score: 3.4) — Proposes routing considerations for AI agent-to-agent communication in overlay networks. Focuses on - **[draft-kartha-internet20-ainative](https://datatracker.ietf.org/doc/draft-kartha-internet20-ainative/)** (score: 3.4) — Proposes Internet 2.0 architecture with AI models as first-class network entities, including HTTP+AI - **[draft-jimenez-tbd-robotstxt-update](https://datatracker.ietf.org/doc/draft-jimenez-tbd-robotstxt-update/)** (score: 3.4) — Proposes updates to robots.txt standard to handle AI-specific crawlers with new syntax for user-agen - **[draft-stephan-ai-agent-6g](https://datatracker.ietf.org/doc/draft-stephan-ai-agent-6g/)** (score: 3.4) — Examines AI agent communication protocols specifically for 6G systems based on 3GPP requirements. Ex - **[draft-zeng-nmrg-mcp-usecases-requirements](https://datatracker.ietf.org/doc/draft-zeng-nmrg-mcp-usecases-requirements/)** (score: 3.4) — Presents problem statement for integrating Model Context Protocol into network management for AI age - **[draft-sz-dmsc-iaip](https://datatracker.ietf.org/doc/draft-sz-dmsc-iaip/)** (score: 3.3) — Defines Intent-based Agent Interconnection Protocol (IAIP) for dynamic agent discovery and routing a - **[draft-jeong-opsawg-intent-based-sdv-framework](https://datatracker.ietf.org/doc/draft-jeong-opsawg-intent-based-sdv-framework/)** (score: 3.3) — Proposes intent-based management framework for Software-Defined Vehicles in ITS environments. Covers - **[draft-liu-rtgwg-agent-gateway-requirements](https://datatracker.ietf.org/doc/draft-liu-rtgwg-agent-gateway-requirements/)** (score: 3.2) — Discusses requirements for Agent Gateways in agent-to-agent communications to improve scalability, e - **[draft-pioli-agent-discovery](https://datatracker.ietf.org/doc/draft-pioli-agent-discovery/)** (score: 3.2) — Specifies ARDP, a lightweight protocol for agent registration and discovery in distributed environme - **[draft-gaikwad-woa](https://datatracker.ietf.org/doc/draft-gaikwad-woa/)** (score: 3.2) — Specifies Web of Agents (WoA) format using JSON Schema to describe AI agent inputs/outputs served fr ## Agent identity/auth (75 drafts) - **[draft-cowles-volt](https://datatracker.ietf.org/doc/draft-cowles-volt/)** (score: 4.8) — Defines tamper-evident execution trace format for AI agent workflows using hash chains and cryptogra - **[draft-aylward-daap-v2](https://datatracker.ietf.org/doc/draft-aylward-daap-v2/)** (score: 4.8) — Defines comprehensive protocol for AI agent accountability including authentication, monitoring, and - **[draft-guy-bary-stamp-protocol](https://datatracker.ietf.org/doc/draft-guy-bary-stamp-protocol/)** (score: 4.6) — Defines STAMP protocol for cryptographic delegation and proof in AI agent systems. Provides task-bou - **[draft-drake-email-tpm-attestation](https://datatracker.ietf.org/doc/draft-drake-email-tpm-attestation/)** (score: 4.6) — Defines hardware attestation for email using TPM verification chains to prevent spam and provide Syb - **[draft-williams-netmod-lm-hierarchy-topology](https://datatracker.ietf.org/doc/draft-williams-netmod-lm-hierarchy-topology/)** (score: 4.6) — Defines YANG data model for hierarchical language model coordination across tiny, small, and large L - **[draft-ietf-lake-app-profiles](https://datatracker.ietf.org/doc/draft-ietf-lake-app-profiles/)** (score: 4.6) — Defines canonical CBOR representation for EDHOC application profiles and coordination mechanisms for - **[draft-goswami-agentic-jwt](https://datatracker.ietf.org/doc/draft-goswami-agentic-jwt/)** (score: 4.5) — Extends OAuth 2.0 with Agentic JWT to address authorization challenges in autonomous AI systems. Int - **[draft-wang-cats-odsi](https://datatracker.ietf.org/doc/draft-wang-cats-odsi/)** (score: 4.5) — Specifies framework for decentralized LLM inference across untrusted participants with layer-aware e - **[draft-aylward-aiga-2](https://datatracker.ietf.org/doc/draft-aylward-aiga-2/)** (score: 4.5) — Comprehensive AI governance framework with tiered risk model, federated authority network, and econo - **[draft-ietf-anima-constrained-voucher](https://datatracker.ietf.org/doc/draft-ietf-anima-constrained-voucher/)** (score: 4.3) — Adapts BRSKI secure device onboarding for constrained IoT environments using CBOR vouchers and CoAP/ - **[draft-ietf-hpke-hpke](https://datatracker.ietf.org/doc/draft-ietf-hpke-hpke/)** (score: 4.3) — Comprehensive specification for hybrid public key encryption supporting arbitrary-sized plaintexts. - **[draft-mw-wimse-transitive-attestation](https://datatracker.ietf.org/doc/draft-mw-wimse-transitive-attestation/)** (score: 4.3) — Defines WIMSE profile for cryptographically binding workload identities to their execution environme - **[draft-dhir-http-agent-profile](https://datatracker.ietf.org/doc/draft-dhir-http-agent-profile/)** (score: 4.2) — Defines HTTP Agent Profile for authenticating agent traffic, separating human from agent traffic, an - **[draft-chen-oauth-rar-agent-extensions](https://datatracker.ietf.org/doc/draft-chen-oauth-rar-agent-extensions/)** (score: 4.2) — Extends OAuth RAR with policy_context and lifecycle_binding members for AI agent environments. Enabl - **[draft-aylward-aiga-1](https://datatracker.ietf.org/doc/draft-aylward-aiga-1/)** (score: 4.2) — Specifies AI Governance and Accountability Protocol with tiered risk-based governance model. Include - **[draft-aap-oauth-profile](https://datatracker.ietf.org/doc/draft-aap-oauth-profile/)** (score: 4.2) — Defines an OAuth 2.0 authorization profile specifically for autonomous AI agents, extending existing - **[draft-narajala-ans](https://datatracker.ietf.org/doc/draft-narajala-ans/)** (score: 4.2) — Introduces Agent Name Service (ANS) as a DNS-based universal directory for AI agent discovery and ve - **[draft-oauth-transaction-tokens-for-agents](https://datatracker.ietf.org/doc/draft-oauth-transaction-tokens-for-agents/)** (score: 4.2) — Extends OAuth Transaction Tokens framework to support agent context propagation with actor and princ - **[draft-zhang-dmsc-mas-communication](https://datatracker.ietf.org/doc/draft-zhang-dmsc-mas-communication/)** (score: 4.2) — Analyzes security risks in multi-agent communication and limitations of existing protocols like TLS - **[draft-li-dmsc-macp](https://datatracker.ietf.org/doc/draft-li-dmsc-macp/)** (score: 4.2) — Specifies a comprehensive multi-agent collaboration protocol suite using Agent Gateways for registra - **[draft-lake-pocero-authkem-ikr-edhoc](https://datatracker.ietf.org/doc/draft-lake-pocero-authkem-ikr-edhoc/)** (score: 4.2) — Specifies an optimized KEM-based authentication variant for EDHOC protocol in scenarios where the in - **[draft-cui-dns-native-agent-naming-resolution](https://datatracker.ietf.org/doc/draft-cui-dns-native-agent-naming-resolution/)** (score: 4.1) — Specifies DNS-native naming and resolution for AI agents using FQDNs and SVCB records. Emphasizes DN - **[draft-liu-agent-operation-authorization](https://datatracker.ietf.org/doc/draft-liu-agent-operation-authorization/)** (score: 4.1) — Specifies framework for verifiable delegation of actions from humans to AI agents using JWT tokens. - **[draft-schulze-ecap](https://datatracker.ietf.org/doc/draft-schulze-ecap/)** (score: 4.1) — ECAP defines a cryptographically-verified protocol for web crawlers to obtain consent from hosts bef - **[draft-mw-spice-actor-chain](https://datatracker.ietf.org/doc/draft-mw-spice-actor-chain/)** (score: 4.1) — Extends OAuth 2.0 Token Exchange with cryptographically verifiable actor chains to provide tamper-ev - **[draft-spm-lake-pqsuites](https://datatracker.ietf.org/doc/draft-spm-lake-pqsuites/)** (score: 4.1) — Defines quantum-resistant cipher suites for EDHOC using ML-DSA signatures and ML-KEM key exchange. S - **[draft-mishra-oauth-agent-grants](https://datatracker.ietf.org/doc/draft-mishra-oauth-agent-grants/)** (score: 4.0) — Extends OAuth 2.0 for AI agent authorization with human consent verification, revocation, and audit - **[draft-barney-caam](https://datatracker.ietf.org/doc/draft-barney-caam/)** (score: 4.0) — Specifies Contextual Agent Authorization Mesh for runtime authorization of agents after discovery, p - **[draft-nennemann-wimse-ect](https://datatracker.ietf.org/doc/draft-nennemann-wimse-ect/)** (score: 4.0) — Defines Execution Context Tokens as JWT extension to WIMSE for tracking task execution in distribute - **[draft-ietf-lake-authz](https://datatracker.ietf.org/doc/draft-ietf-lake-authz/)** (score: 3.9) — Specifies lightweight authorization using EDHOC for zero-touch device onboarding. Enables secure enr - **[draft-ietf-ace-coap-est-oscore](https://datatracker.ietf.org/doc/draft-ietf-ace-coap-est-oscore/)** (score: 3.9) — Specifies carrying EST certificate provisioning over CoAP using OSCORE protection instead of DTLS. B - **[draft-berlinai-vera](https://datatracker.ietf.org/doc/draft-berlinai-vera/)** (score: 3.9) — Introduces VERA, a zero-trust architecture for AI agent security with five enforcement pillars and c - **[draft-josefsson-chempat](https://datatracker.ietf.org/doc/draft-josefsson-chempat/)** (score: 3.9) — Generic framework for Post-Quantum/Traditional hybrid key encapsulation mechanisms. Provides concret - **[draft-ravikiran-clawdentity-protocol](https://datatracker.ietf.org/doc/draft-ravikiran-clawdentity-protocol/)** (score: 3.9) — Specifies Clawdentity protocol for cryptographic identity and trust in AI agent communication. Provi - **[draft-bradleylundberg-cfrg-arkg](https://datatracker.ietf.org/doc/draft-bradleylundberg-cfrg-arkg/)** (score: 3.9) — Defines Asynchronous Remote Key Generation algorithm enabling delegation of public key generation wi - **[draft-tsyrulnikov-rats-attested-inference-receipt](https://datatracker.ietf.org/doc/draft-tsyrulnikov-rats-attested-inference-receipt/)** (score: 3.9) — Defines Attested Inference Receipt (AIR) using COSE/CWT to create verifiable receipts for confidenti - **[draft-ramadan-mboned-sonar](https://datatracker.ietf.org/doc/draft-ramadan-mboned-sonar/)** (score: 3.8) — Specifies a protocol for verifiable multicast delivery using cryptoeconomic accountability and stati - **[draft-ietf-emu-hybrid-pqc-eapaka](https://datatracker.ietf.org/doc/draft-ietf-emu-hybrid-pqc-eapaka/)** (score: 3.8) — Enhances EAP-AKA' with post-quantum cryptography to address quantum computing threats. Uses hybrid P - **[draft-chen-ai-agent-auth-new-requirements](https://datatracker.ietf.org/doc/draft-chen-ai-agent-auth-new-requirements/)** (score: 3.8) — Identifies new authentication and authorization requirements for AI agents that go beyond traditiona - **[draft-sogomonian-ai-uri-scheme](https://datatracker.ietf.org/doc/draft-sogomonian-ai-uri-scheme/)** (score: 3.8) — Defines experimental AI URI scheme for dedicated AI resource access. Enables native connectivity for - **[draft-srijal-agents-policy](https://datatracker.ietf.org/doc/draft-srijal-agents-policy/)** (score: 3.8) — Specifies AGENTS.TXT protocol as strict plaintext policy file for automated clients, bots, and crawl - **[draft-abbey-scim-agent-extension](https://datatracker.ietf.org/doc/draft-abbey-scim-agent-extension/)** (score: 3.8) — Extends SCIM 2.0 protocol to manage AI agents and agentic applications across domains. Adds new sche - **[draft-eckert-anima-acp-free-ani](https://datatracker.ietf.org/doc/draft-eckert-anima-acp-free-ani/)** (score: 3.8) — Describes lightweight variation of Autonomic Networking Infrastructure without expensive ACP impleme - **[draft-scim-agent-extension](https://datatracker.ietf.org/doc/draft-scim-agent-extension/)** (score: 3.7) — Extends SCIM 2.0 specification to manage agents and agentic applications across domains. Builds on e - **[draft-zheng-agent-identity-management](https://datatracker.ietf.org/doc/draft-zheng-agent-identity-management/)** (score: 3.7) — Defines comprehensive agent identity management for Internet of Agents systems. Covers agent registr - **[draft-melnikov-sasl2](https://datatracker.ietf.org/doc/draft-melnikov-sasl2/)** (score: 3.7) — Updates SASL framework to support modern authentication requirements including multi-factor authenti - **[draft-ietf-lamps-attestation-freshness](https://datatracker.ietf.org/doc/draft-ietf-lamps-attestation-freshness/)** (score: 3.7) — Outlines how nonces are supplied to end entities by RA/CA for inclusion in attestation evidence with - **[draft-ietf-lake-ra](https://datatracker.ietf.org/doc/draft-ietf-lake-ra/)** (score: 3.7) — Specifies remote attestation procedures integrated with EDHOC lightweight key exchange protocol. Ena - **[draft-gaikwad-south-authorization](https://datatracker.ietf.org/doc/draft-gaikwad-south-authorization/)** (score: 3.7) — Authorization protocol supporting probabilistic decisions for agents and services. Enables uncertain - **[draft-sogomonian-aiip-architecture](https://datatracker.ietf.org/doc/draft-sogomonian-aiip-architecture/)** (score: 3.7) — Defines architectural model for Artificial Intelligence Internet Protocol (AIIP) enabling stateless, - **[draft-ni-a2a-ai-agent-security-requirements](https://datatracker.ietf.org/doc/draft-ni-a2a-ai-agent-security-requirements/)** (score: 3.7) — Establishes security requirements for AI agents across their operational lifecycle. Covers provision - **[draft-pocero-authkem-edhoc](https://datatracker.ietf.org/doc/draft-pocero-authkem-edhoc/)** (score: 3.7) — Extends EDHOC with KEM-based authentication for post-quantum resistance. Enables signature-free quan - **[draft-zyyhl-agent-networks-framework](https://datatracker.ietf.org/doc/draft-zyyhl-agent-networks-framework/)** (score: 3.6) — Defines comprehensive framework for AI agent networks based on Agent Network Protocol (ANP). Provide - **[draft-rosenberg-oauth-aauth](https://datatracker.ietf.org/doc/draft-rosenberg-oauth-aauth/)** (score: 3.6) — Extends OAuth 2.1 for AI agents operating through PSTN/SMS channels to obtain access tokens using PI - **[draft-mozleywilliams-dnsop-bandaid](https://datatracker.ietf.org/doc/draft-mozleywilliams-dnsop-bandaid/)** (score: 3.6) — Proposes using DNS with SVCB records to enable AI agent discovery and capability advertisement. Leve - **[draft-vandoulas-aidp](https://datatracker.ietf.org/doc/draft-vandoulas-aidp/)** (score: 3.6) — Defines a comprehensive control-plane protocol for secure agent interactions with delegation, author - **[draft-messous-eat-ai](https://datatracker.ietf.org/doc/draft-messous-eat-ai/)** (score: 3.6) — Defines an Entity Attestation Token profile for remote attestation of autonomous AI agents, specifyi - **[draft-ietf-ace-edhoc-oscore-profile](https://datatracker.ietf.org/doc/draft-ietf-ace-edhoc-oscore-profile/)** (score: 3.6) — Defines ACE framework profile using EDHOC for mutual authentication and OSCORE for secure communicat - **[draft-liu-oauth-a2a-profile](https://datatracker.ietf.org/doc/draft-liu-oauth-a2a-profile/)** (score: 3.6) — Specifies OAuth Transaction Token profile for Agent-to-Agent communication. Embeds call chain contex - **[draft-liu-dmsc-acps-arc](https://datatracker.ietf.org/doc/draft-liu-dmsc-acps-arc/)** (score: 3.6) — Proposes Agent Collaboration Protocols architecture for Internet of Agents, covering agent lifecycle - **[draft-liang-agentdns](https://datatracker.ietf.org/doc/draft-liang-agentdns/)** (score: 3.5) — Proposes a DNS-inspired naming and service discovery system for LLM agents to enable autonomous disc - **[draft-song-oauth-ai-agent-collaborate-authz](https://datatracker.ietf.org/doc/draft-song-oauth-ai-agent-collaborate-authz/)** (score: 3.5) — Proposes OAuth 2.0 extension for multi-AI agent collaboration with applier-on-behalf-of authorizatio - **[draft-ahn-nmrg-5g-security-i2nsf-framework](https://datatracker.ietf.org/doc/draft-ahn-nmrg-5g-security-i2nsf-framework/)** (score: 3.5) — Presents integrated framework for automated 5G edge network security using I2NSF architecture and In - **[draft-jia-oauth-scope-aggregation](https://datatracker.ietf.org/doc/draft-jia-oauth-scope-aggregation/)** (score: 3.5) — Extends OAuth 2.0 with scope aggregation to reduce authorization round-trips in multi-step AI agent - **[draft-ietf-emu-pqc-eapaka](https://datatracker.ietf.org/doc/draft-ietf-emu-pqc-eapaka/)** (score: 3.5) — This draft proposes enhancing EAP-AKA' Forward Secrecy with Post-Quantum Key Encapsulation Mechanism - **[draft-zhang-rvp-problem-statement](https://datatracker.ietf.org/doc/draft-zhang-rvp-problem-statement/)** (score: 3.5) — Proposes Real-Virtual Agent Protocol for coordinating physical entities with digital agents through - **[draft-li-dmsc-mcps-agw](https://datatracker.ietf.org/doc/draft-li-dmsc-mcps-agw/)** (score: 3.5) — Defines a protocol suite using Agent Gateways as control-plane entities for multi-agent collaboratio - **[draft-ar-emu-hybrid-pqc-eapaka](https://datatracker.ietf.org/doc/draft-ar-emu-hybrid-pqc-eapaka/)** (score: 3.5) — Enhances EAP-AKA' with hybrid post-quantum cryptography combining traditional and quantum-resistant - **[draft-huang-rats-agentic-eat-cap-attest](https://datatracker.ietf.org/doc/draft-huang-rats-agentic-eat-cap-attest/)** (score: 3.4) — Extends Entity Attestation Token (EAT) to support capability attestation for agentic AI systems. Ena - **[draft-jiang-seat-dynamic-attestation](https://datatracker.ietf.org/doc/draft-jiang-seat-dynamic-attestation/)** (score: 3.4) — Defines dynamic attestation mechanisms for AI agents to convey runtime posture changes during long-l - **[draft-ramakrishna-satp-views-addresses](https://datatracker.ietf.org/doc/draft-ramakrishna-satp-views-addresses/)** (score: 3.4) — Defines view and addressing mechanisms for secure asset transfer between DLT systems. Enables cross- - **[draft-cosmos-protocol-specification](https://datatracker.ietf.org/doc/draft-cosmos-protocol-specification/)** (score: 3.3) — Defines comprehensive badge-based identity and communication system with trust scoring, post-quantum - **[draft-liu-rtgwg-agent-gateway-requirements](https://datatracker.ietf.org/doc/draft-liu-rtgwg-agent-gateway-requirements/)** (score: 3.2) — Discusses requirements for Agent Gateways in agent-to-agent communications to improve scalability, e - **[draft-pioli-agent-discovery](https://datatracker.ietf.org/doc/draft-pioli-agent-discovery/)** (score: 3.2) — Specifies ARDP, a lightweight protocol for agent registration and discovery in distributed environme - **[draft-diaconu-agents-authz-info-sharing](https://datatracker.ietf.org/doc/draft-diaconu-agents-authz-info-sharing/)** (score: 3.2) — Addresses authorization challenges in distributed multi-agent systems across multiple domains. Cover ## Agent-to-agent communication protocols (5 drafts) - **[draft-nandakumar-agent-sd-jwt](https://datatracker.ietf.org/doc/draft-nandakumar-agent-sd-jwt/)** (score: 3.9) — This draft defines SD-Card, a Selective Disclosure JWT encoding of Agent Cards that enables privacy- - **[draft-oauth-ai-agents-on-behalf-of-user](https://datatracker.ietf.org/doc/draft-oauth-ai-agents-on-behalf-of-user/)** (score: 3.7) — This draft extends OAuth 2.0 to enable AI agents to securely obtain access tokens for acting on beha - **[draft-liu-agent-context-protocol](https://datatracker.ietf.org/doc/draft-liu-agent-context-protocol/)** (score: 3.5) — This draft proposes a standard protocol for AI agents to communicate context information to each oth - **[draft-zheng-dispatch-agent-identity-management](https://datatracker.ietf.org/doc/draft-zheng-dispatch-agent-identity-management/)** (score: 3.3) — This draft proposes an identity management framework for agents in an Internet of Agents (IOA) syste - **[draft-narvaneni-agent-uri](https://datatracker.ietf.org/doc/draft-narvaneni-agent-uri/)** (score: 3.3) — This draft defines the agent:// URI scheme for addressing and interoperating with software agents ac ## Autonomous netops (46 drafts) - **[draft-cui-nmrg-llm-benchmark](https://datatracker.ietf.org/doc/draft-cui-nmrg-llm-benchmark/)** (score: 4.3) — Provides comprehensive evaluation framework for LLM-based network configuration agents. Includes emu - **[draft-wmz-nmrg-agent-ndt-arch](https://datatracker.ietf.org/doc/draft-wmz-nmrg-agent-ndt-arch/)** (score: 4.2) — Comprehensive architecture combining Network Digital Twin with Agentic AI for intent-based network o - **[draft-yue-anima-agent-recovery-networks](https://datatracker.ietf.org/doc/draft-yue-anima-agent-recovery-networks/)** (score: 4.1) — Defines task-oriented multi-agent framework for fault recovery in converged mobile networks. Targets - **[draft-cui-nmrg-llm-nm](https://datatracker.ietf.org/doc/draft-cui-nmrg-llm-nm/)** (score: 4.1) — Defines framework for collaborative network management between LLM agents and human operators. Intro - **[draft-jadoon-nmrg-agentic-ai-autonomous-networks](https://datatracker.ietf.org/doc/draft-jadoon-nmrg-agentic-ai-autonomous-networks/)** (score: 4.1) — Introduces architectural principles for integrating AI agents into IP protocol stack layers while pr - **[draft-chen-nmrg-semantic-inference-routing](https://datatracker.ietf.org/doc/draft-chen-nmrg-semantic-inference-routing/)** (score: 4.1) — Defines SIRP protocol for content-aware routing of AI inference requests. Enables routing decisions - **[draft-ietf-lisp-nexagon](https://datatracker.ietf.org/doc/draft-ietf-lisp-nexagon/)** (score: 4.0) — Combines LISP with H3 spatial indexing to create geospatial intelligence network for physical-world - **[draft-han-anima-ai-asa](https://datatracker.ietf.org/doc/draft-han-anima-ai-asa/)** (score: 4.0) — Analyzes the impact of enhancing ANIMA's Autonomic Service Agents with AI/LLM capabilities, focusing - **[draft-zeng-opsawg-llm-netconf-gap](https://datatracker.ietf.org/doc/draft-zeng-opsawg-llm-netconf-gap/)** (score: 3.9) — Analyzes gaps in existing network configuration protocols for LLM-driven intent-based networking. Id - **[draft-templin-intarea-aero2](https://datatracker.ietf.org/doc/draft-templin-intarea-aero2/)** (score: 3.9) — Specifies AERO service for IP internetworking over overlay multilink networks using IPv6 ND for cont - **[draft-luan-rtgwg-sdaf](https://datatracker.ietf.org/doc/draft-luan-rtgwg-sdaf/)** (score: 3.8) — Proposes symmetry-driven forwarding mechanism for LEO satellite networks to avoid routing loops and - **[draft-zhao-nmop-network-management-agent](https://datatracker.ietf.org/doc/draft-zhao-nmop-network-management-agent/)** (score: 3.8) — Defines AI-driven Network Management Agent concept for Level 4 autonomous networks. Specifies integr - **[draft-eckert-anima-acp-free-ani](https://datatracker.ietf.org/doc/draft-eckert-anima-acp-free-ani/)** (score: 3.8) — Describes lightweight variation of Autonomic Networking Infrastructure without expensive ACP impleme - **[draft-yuan-rtgwg-traffic-agent-usecase](https://datatracker.ietf.org/doc/draft-yuan-rtgwg-traffic-agent-usecase/)** (score: 3.7) — Presents use cases for AI agents optimizing network traffic through dynamic resource adjustment. Det - **[draft-ietf-netconf-configuration-tracing](https://datatracker.ietf.org/doc/draft-ietf-netconf-configuration-tracing/)** (score: 3.7) — Specifies a NETCONF mechanism to map configuration modifications to their originating NMS using exte - **[draft-mao-rtgwg-agent-comm-protocol-gap-analysis](https://datatracker.ietf.org/doc/draft-mao-rtgwg-agent-comm-protocol-gap-analysis/)** (score: 3.6) — Analyzes gaps in existing networking and AI protocols for cross-device communication between AI agen - **[draft-zlgsgl-rtgwg-agents-networking-framework](https://datatracker.ietf.org/doc/draft-zlgsgl-rtgwg-agents-networking-framework/)** (score: 3.6) — Introduces a comprehensive agents networking framework for enterprise and broadband environments. De - **[draft-han-rtgwg-agent-gateway-intercomm-framework](https://datatracker.ietf.org/doc/draft-han-rtgwg-agent-gateway-intercomm-framework/)** (score: 3.6) — Defines framework for intercommunication between Agent Gateways in Agent Internet ecosystem. Address - **[draft-zm-rtgwg-mcp-troubleshooting](https://datatracker.ietf.org/doc/draft-zm-rtgwg-mcp-troubleshooting/)** (score: 3.6) — Proposes using Model Context Protocol (MCP) to enable LLM-based automated network troubleshooting. M - **[draft-li-semantic-routing-architecture](https://datatracker.ietf.org/doc/draft-li-semantic-routing-architecture/)** (score: 3.6) — Introduces semantic routing architecture using intent vectors and trust scores for AI agent communic - **[draft-cui-nmrg-auto-test](https://datatracker.ietf.org/doc/draft-cui-nmrg-auto-test/)** (score: 3.6) — Framework for AI-assisted network protocol testing using LLMs and automated test generation. Defines - **[draft-xsaopig-nsttlp-traffic-labeling](https://datatracker.ietf.org/doc/draft-xsaopig-nsttlp-traffic-labeling/)** (score: 3.6) — Specifies protocol for embedding service type identifiers in network packets to enable intelligent t - **[draft-moreno-lisp-uberlay](https://datatracker.ietf.org/doc/draft-moreno-lisp-uberlay/)** (score: 3.6) — Describes using LISP to interconnect multiple independent network overlays through a transit overlay - **[draft-templin-6man-aero3](https://datatracker.ietf.org/doc/draft-templin-6man-aero3/)** (score: 3.6) — Specifies automatic extended route optimization for IP internetworking over overlay multilink networ - **[draft-liu-dmsc-acps-arc](https://datatracker.ietf.org/doc/draft-liu-dmsc-acps-arc/)** (score: 3.6) — Proposes Agent Collaboration Protocols architecture for Internet of Agents, covering agent lifecycle - **[draft-pbs-sidrops-roaanycast](https://datatracker.ietf.org/doc/draft-pbs-sidrops-roaanycast/)** (score: 3.6) — Defines best practices for managing Route Origin Authorizations (ROAs) for globally anycasted servic - **[draft-ye-problems-and-requirements-of-dns-for-ioa](https://datatracker.ietf.org/doc/draft-ye-problems-and-requirements-of-dns-for-ioa/)** (score: 3.5) — Analyzes DNS challenges for Internet of Agents scenarios and identifies technical requirements. Expl - **[draft-irtf-nmrg-llm-nm](https://datatracker.ietf.org/doc/draft-irtf-nmrg-llm-nm/)** (score: 3.5) — Defines framework for collaborative network management between LLMs and human operators with human-i - **[draft-zeng-mcp-network-measurement](https://datatracker.ietf.org/doc/draft-zeng-mcp-network-measurement/)** (score: 3.5) — Proposes MCP framework for intelligent network measurement with AI assistance. Enables natural langu - **[draft-templin-intarea-aero](https://datatracker.ietf.org/doc/draft-templin-intarea-aero/)** (score: 3.5) — Specifies Automatic Extended Route Optimization (AERO) service for IP internetworking over Overlay M - **[draft-ahn-nmrg-5g-security-i2nsf-framework](https://datatracker.ietf.org/doc/draft-ahn-nmrg-5g-security-i2nsf-framework/)** (score: 3.5) — Presents integrated framework for automated 5G edge network security using I2NSF architecture and In - **[draft-zhang-rvp-problem-statement](https://datatracker.ietf.org/doc/draft-zhang-rvp-problem-statement/)** (score: 3.5) — Proposes Real-Virtual Agent Protocol for coordinating physical entities with digital agents through - **[draft-zeng-opsawg-applicability-mcp-a2a](https://datatracker.ietf.org/doc/draft-zeng-opsawg-applicability-mcp-a2a/)** (score: 3.5) — Analyzes NETCONF limitations for advanced scenarios and proposes MCP and A2A protocols as complement - **[draft-yuan-rtgwg-security-agent-usecase](https://datatracker.ietf.org/doc/draft-yuan-rtgwg-security-agent-usecase/)** (score: 3.4) — Proposes AI Network Security Agents for routers to provide intelligent, adaptive security capabiliti - **[draft-kartha-grd](https://datatracker.ietf.org/doc/draft-kartha-grd/)** (score: 3.4) — Defines architectural framework for discovering network resources based on physical location and con - **[draft-tan-ccamp-uonaco-problem-statement](https://datatracker.ietf.org/doc/draft-tan-ccamp-uonaco-problem-statement/)** (score: 3.4) — Defines requirements for unified orchestration between optical networks and AI computing to enable c - **[draft-yan-a2a-device-agent-applicability](https://datatracker.ietf.org/doc/draft-yan-a2a-device-agent-applicability/)** (score: 3.4) — Discusses applying Agent-to-Agent (A2A) Protocol to network management for communication between Con - **[draft-yue-moq-transporting-sensing-data](https://datatracker.ietf.org/doc/draft-yue-moq-transporting-sensing-data/)** (score: 3.4) — Proposes using Media Over QUIC (MOQ) to transport large-scale, real-time sensing data in 6G networks - **[draft-zw-rtgwg-mcp-network-mgmt](https://datatracker.ietf.org/doc/draft-zw-rtgwg-mcp-network-mgmt/)** (score: 3.4) — Specifies MCP extensions for network equipment management with routers/switches as MCP servers. Defi - **[draft-zeng-nmrg-mcp-usecases-requirements](https://datatracker.ietf.org/doc/draft-zeng-nmrg-mcp-usecases-requirements/)** (score: 3.4) — Presents problem statement for integrating Model Context Protocol into network management for AI age - **[draft-zhu-anima-service-intent](https://datatracker.ietf.org/doc/draft-zhu-anima-service-intent/)** (score: 3.4) — Defines a structured semantic model for expressing service-level objectives and constraints across n - **[draft-xsaopig-nmop-service-flow-modal-mapping](https://datatracker.ietf.org/doc/draft-xsaopig-nmop-service-flow-modal-mapping/)** (score: 3.3) — Proposes a framework using ALTO protocol and SDN architecture for mapping service flow characteristi - **[draft-jeong-opsawg-intent-based-sdv-framework](https://datatracker.ietf.org/doc/draft-jeong-opsawg-intent-based-sdv-framework/)** (score: 3.3) — Proposes intent-based management framework for Software-Defined Vehicles in ITS environments. Covers - **[draft-bernardos-nmrg-agentic-network-optimization](https://datatracker.ietf.org/doc/draft-bernardos-nmrg-agentic-network-optimization/)** (score: 3.3) — Focuses on agentic AI for distributed sensing in ISAC networks with joint optimization of sensing an - **[draft-chuyi-nmrg-ai-agent-network](https://datatracker.ietf.org/doc/draft-chuyi-nmrg-ai-agent-network/)** (score: 3.2) — Focuses on large language model-based agents for network operations and maintenance. Addresses pract - **[draft-ahn-opsawg-5g-security-i2nsf-framework](https://datatracker.ietf.org/doc/draft-ahn-opsawg-5g-security-i2nsf-framework/)** (score: 3.2) — Proposes an integrated security framework for 5G edge networks using I2NSF architecture with Intent- ## Data formats / semantics for AI interop (2 drafts) - **[draft-liu-agent-context-protocol](https://datatracker.ietf.org/doc/draft-liu-agent-context-protocol/)** (score: 3.5) — This draft proposes a standard protocol for AI agents to communicate context information to each oth - **[draft-narvaneni-agent-uri](https://datatracker.ietf.org/doc/draft-narvaneni-agent-uri/)** (score: 3.3) — This draft defines the agent:// URI scheme for addressing and interoperating with software agents ac ## Data formats/interop (85 drafts) - **[draft-cowles-volt](https://datatracker.ietf.org/doc/draft-cowles-volt/)** (score: 4.8) — Defines tamper-evident execution trace format for AI agent workflows using hash chains and cryptogra - **[draft-williams-netmod-lm-hierarchy-topology](https://datatracker.ietf.org/doc/draft-williams-netmod-lm-hierarchy-topology/)** (score: 4.6) — Defines YANG data model for hierarchical language model coordination across tiny, small, and large L - **[draft-ietf-lake-app-profiles](https://datatracker.ietf.org/doc/draft-ietf-lake-app-profiles/)** (score: 4.6) — Defines canonical CBOR representation for EDHOC application profiles and coordination mechanisms for - **[draft-chang-agent-token-efficient](https://datatracker.ietf.org/doc/draft-chang-agent-token-efficient/)** (score: 4.5) — Defines ADOL (Agentic Data Optimization Layer) to address token bloat in agent communication protoco - **[draft-birkholz-verifiable-agent-conversations](https://datatracker.ietf.org/doc/draft-birkholz-verifiable-agent-conversations/)** (score: 4.5) — Defines CDDL-based data format for verifiable agent conversation records using COSE signing. Support - **[draft-ietf-aipref-vocab](https://datatracker.ietf.org/doc/draft-ietf-aipref-vocab/)** (score: 4.4) — Defines a standardized vocabulary for expressing preferences about how digital assets should be used - **[draft-cui-nmrg-llm-benchmark](https://datatracker.ietf.org/doc/draft-cui-nmrg-llm-benchmark/)** (score: 4.3) — Provides comprehensive evaluation framework for LLM-based network configuration agents. Includes emu - **[draft-ietf-anima-constrained-voucher](https://datatracker.ietf.org/doc/draft-ietf-anima-constrained-voucher/)** (score: 4.3) — Adapts BRSKI secure device onboarding for constrained IoT environments using CBOR vouchers and CoAP/ - **[draft-ietf-hpke-hpke](https://datatracker.ietf.org/doc/draft-ietf-hpke-hpke/)** (score: 4.3) — Comprehensive specification for hybrid public key encryption supporting arbitrary-sized plaintexts. - **[draft-mallick-muacp](https://datatracker.ietf.org/doc/draft-mallick-muacp/)** (score: 4.2) — Resource-efficient messaging protocol specifically designed for constrained IoT/Edge devices with de - **[draft-gaikwad-llm-benchmarking-methodology](https://datatracker.ietf.org/doc/draft-gaikwad-llm-benchmarking-methodology/)** (score: 4.2) — Defines comprehensive benchmarking methodologies for LLM inference serving systems including test pr - **[draft-ietf-sshm-mlkem-hybrid-kex](https://datatracker.ietf.org/doc/draft-ietf-sshm-mlkem-hybrid-kex/)** (score: 4.2) — Defines post-quantum hybrid key exchange combining ML-KEM with traditional ECDH for SSH transport la - **[draft-ietf-tls-extended-key-update](https://datatracker.ietf.org/doc/draft-ietf-tls-extended-key-update/)** (score: 4.2) — Adds post-compromise security to TLS 1.3 through fresh Diffie-Hellman exchanges during active sessio - **[draft-calabria-bmwg-ai-fabric-terminology](https://datatracker.ietf.org/doc/draft-calabria-bmwg-ai-fabric-terminology/)** (score: 4.2) — Defines comprehensive benchmarking terminology for AI network fabrics including collective communica - **[draft-narajala-ans](https://datatracker.ietf.org/doc/draft-narajala-ans/)** (score: 4.2) — Introduces Agent Name Service (ANS) as a DNS-based universal directory for AI agent discovery and ve - **[draft-li-dmsc-macp](https://datatracker.ietf.org/doc/draft-li-dmsc-macp/)** (score: 4.2) — Specifies a comprehensive multi-agent collaboration protocol suite using Agent Gateways for registra - **[draft-gaikwad-llm-benchmarking-profiles](https://datatracker.ietf.org/doc/draft-gaikwad-llm-benchmarking-profiles/)** (score: 4.2) — Defines performance benchmarking profiles binding terminology and methodology to concrete architectu - **[draft-cui-dns-native-agent-naming-resolution](https://datatracker.ietf.org/doc/draft-cui-dns-native-agent-naming-resolution/)** (score: 4.1) — Specifies DNS-native naming and resolution for AI agents using FQDNs and SVCB records. Emphasizes DN - **[draft-nederveld-adl](https://datatracker.ietf.org/doc/draft-nederveld-adl/)** (score: 4.1) — Defines ADL, a JSON-based standard for describing AI agents including their capabilities, tools, per - **[draft-steele-agent-considerations](https://datatracker.ietf.org/doc/draft-steele-agent-considerations/)** (score: 4.0) — Defines guidelines for IETF specifications to support AI agent consumption and code generation. Intr - **[draft-chen-nmrg-multi-provider-inference-api](https://datatracker.ietf.org/doc/draft-chen-nmrg-multi-provider-inference-api/)** (score: 4.0) — Specifies extensions for multi-provider AI inference using OpenAI API as reference standard. Enables - **[draft-ietf-lisp-nexagon](https://datatracker.ietf.org/doc/draft-ietf-lisp-nexagon/)** (score: 4.0) — Combines LISP with H3 spatial indexing to create geospatial intelligence network for physical-world - **[draft-nennemann-wimse-ect](https://datatracker.ietf.org/doc/draft-nennemann-wimse-ect/)** (score: 4.0) — Defines Execution Context Tokens as JWT extension to WIMSE for tracking task execution in distribute - **[draft-jennings-ai-mcp-over-moq](https://datatracker.ietf.org/doc/draft-jennings-ai-mcp-over-moq/)** (score: 4.0) — Defines how to transport Model Context Protocol (MCP) messages over Media over QUIC Transport (MOQT) - **[draft-dunbar-neotec-ac-te-applicability](https://datatracker.ietf.org/doc/draft-dunbar-neotec-ac-te-applicability/)** (score: 4.0) — Applies existing IETF YANG models for Attachment Circuits and Traffic Engineering to dynamic AI mode - **[draft-ietf-ace-coap-est-oscore](https://datatracker.ietf.org/doc/draft-ietf-ace-coap-est-oscore/)** (score: 3.9) — Specifies carrying EST certificate provisioning over CoAP using OSCORE protection instead of DTLS. B - **[draft-agent-gw](https://datatracker.ietf.org/doc/draft-agent-gw/)** (score: 3.9) — Proposes an Intelligent Agent Communication Gateway for large-scale multi-agent collaboration. Featu - **[draft-mp-agntcy-ads](https://datatracker.ietf.org/doc/draft-mp-agntcy-ads/)** (score: 3.9) — Describes Agent Directory Service for storing and discovering AI agent metadata based on skills. Fea - **[draft-zeng-opsawg-llm-netconf-gap](https://datatracker.ietf.org/doc/draft-zeng-opsawg-llm-netconf-gap/)** (score: 3.9) — Analyzes gaps in existing network configuration protocols for LLM-driven intent-based networking. Id - **[draft-akhavain-moussa-ai-network](https://datatracker.ietf.org/doc/draft-akhavain-moussa-ai-network/)** (score: 3.9) — Proposes Data and Agent Aware-Inference and Training Network (DA-ITN) architecture. Comprehensive mu - **[draft-rosenberg-aiproto-a2t](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-a2t/)** (score: 3.9) — Defines Agent-to-Tool (A2T) protocol for integrating third-party APIs into AI agent operations. Prov - **[draft-josefsson-chempat](https://datatracker.ietf.org/doc/draft-josefsson-chempat/)** (score: 3.9) — Generic framework for Post-Quantum/Traditional hybrid key encapsulation mechanisms. Provides concret - **[draft-cui-ai-agent-discovery-invocation](https://datatracker.ietf.org/doc/draft-cui-ai-agent-discovery-invocation/)** (score: 3.9) — Proposes standardized protocol for AI agent discovery and invocation with common metadata format and - **[draft-ravikiran-clawdentity-protocol](https://datatracker.ietf.org/doc/draft-ravikiran-clawdentity-protocol/)** (score: 3.9) — Specifies Clawdentity protocol for cryptographic identity and trust in AI agent communication. Provi - **[draft-jurkovikj-httpapi-agentic-state](https://datatracker.ietf.org/doc/draft-jurkovikj-httpapi-agentic-state/)** (score: 3.9) — Defines Agentic State Transfer (AST) HTTP profile for managing canonical resource state across multi - **[draft-tejido-swp-core](https://datatracker.ietf.org/doc/draft-tejido-swp-core/)** (score: 3.9) — Specifies SlimWire Protocol Core, a binary framing layer for agent/tool messaging with profile-based - **[draft-bradleylundberg-cfrg-arkg](https://datatracker.ietf.org/doc/draft-bradleylundberg-cfrg-arkg/)** (score: 3.9) — Defines Asynchronous Remote Key Generation algorithm enabling delegation of public key generation wi - **[draft-tsyrulnikov-rats-attested-inference-receipt](https://datatracker.ietf.org/doc/draft-tsyrulnikov-rats-attested-inference-receipt/)** (score: 3.9) — Defines Attested Inference Receipt (AIR) using COSE/CWT to create verifiable receipts for confidenti - **[draft-templin-intarea-aero2](https://datatracker.ietf.org/doc/draft-templin-intarea-aero2/)** (score: 3.9) — Specifies AERO service for IP internetworking over overlay multilink networks using IPv6 ND for cont - **[draft-ramadan-mboned-sonar](https://datatracker.ietf.org/doc/draft-ramadan-mboned-sonar/)** (score: 3.8) — Specifies a protocol for verifiable multicast delivery using cryptoeconomic accountability and stati - **[draft-sogomonian-ai-uri-scheme](https://datatracker.ietf.org/doc/draft-sogomonian-ai-uri-scheme/)** (score: 3.8) — Defines experimental AI URI scheme for dedicated AI resource access. Enables native connectivity for - **[draft-srijal-agents-policy](https://datatracker.ietf.org/doc/draft-srijal-agents-policy/)** (score: 3.8) — Specifies AGENTS.TXT protocol as strict plaintext policy file for automated clients, bots, and crawl - **[draft-abbey-scim-agent-extension](https://datatracker.ietf.org/doc/draft-abbey-scim-agent-extension/)** (score: 3.8) — Extends SCIM 2.0 protocol to manage AI agents and agentic applications across domains. Adds new sche - **[draft-ietf-aipref-attach](https://datatracker.ietf.org/doc/draft-ietf-aipref-attach/)** (score: 3.8) — Specifies how AI usage preferences can be signaled during HTTP content acquisition. Updates RFC 9309 - **[draft-scim-agent-extension](https://datatracker.ietf.org/doc/draft-scim-agent-extension/)** (score: 3.7) — Extends SCIM 2.0 specification to manage agents and agentic applications across domains. Builds on e - **[draft-rosenberg-aiproto-framework](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-framework/)** (score: 3.7) — Provides framework and requirements for AI agent protocols on the Internet. Surveys existing approac - **[draft-ietf-lamps-rfc7030-csrattrs](https://datatracker.ietf.org/doc/draft-ietf-lamps-rfc7030-csrattrs/)** (score: 3.7) — Updates RFC7030 to clarify CSR Attributes Response encoding and adds template-based approach for EST - **[draft-ietf-suit-firmware-encryption](https://datatracker.ietf.org/doc/draft-ietf-suit-firmware-encryption/)** (score: 3.7) — Specifies encryption techniques for firmware and software payloads in SUIT manifests. Uses ES-DH and - **[draft-ietf-lamps-est-renewal-info](https://datatracker.ietf.org/doc/draft-ietf-lamps-est-renewal-info/)** (score: 3.7) — Extends EST protocol to provide server-side recommendations for certificate renewal timing. Addresse - **[draft-ietf-netconf-configuration-tracing](https://datatracker.ietf.org/doc/draft-ietf-netconf-configuration-tracing/)** (score: 3.7) — Specifies a NETCONF mechanism to map configuration modifications to their originating NMS using exte - **[draft-howe-sipcore-mcp-extension](https://datatracker.ietf.org/doc/draft-howe-sipcore-mcp-extension/)** (score: 3.7) — Defines SIP extension to carry Model Context Protocol with new option-tags, headers, and media types - **[draft-rosenberg-aiproto](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto/)** (score: 3.7) — Defines N-ACT protocol for AI agents to discover and invoke third-party tools and APIs. Focuses on e - **[draft-rosenberg-aiproto-nact](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-nact/)** (score: 3.7) — Defines N-ACT protocol for AI agents to discover and invoke third-party tools and APIs. Focuses on e - **[draft-zyyhl-agent-networks-framework](https://datatracker.ietf.org/doc/draft-zyyhl-agent-networks-framework/)** (score: 3.6) — Defines comprehensive framework for AI agent networks based on Agent Network Protocol (ANP). Provide - **[draft-yang-ioa-protocol](https://datatracker.ietf.org/doc/draft-yang-ioa-protocol/)** (score: 3.6) — Defines the Internet of Agents Protocol for distributed collaboration among heterogeneous AI agents. - **[draft-zm-rtgwg-mcp-troubleshooting](https://datatracker.ietf.org/doc/draft-zm-rtgwg-mcp-troubleshooting/)** (score: 3.6) — Proposes using Model Context Protocol (MCP) to enable LLM-based automated network troubleshooting. M - **[draft-reilly-sentinel-protocol](https://datatracker.ietf.org/doc/draft-reilly-sentinel-protocol/)** (score: 3.6) — Defines blockchain-anchored integrity protocol for AI lifecycle provenance using Sentinel Evidence P - **[draft-altanai-aipref-realtime-protocol-bindings](https://datatracker.ietf.org/doc/draft-altanai-aipref-realtime-protocol-bindings/)** (score: 3.6) — Defines how AI preference expressions are bound to real-time protocols like SIP and SDP. Specifies h - **[draft-mozleywilliams-dnsop-dnsaid](https://datatracker.ietf.org/doc/draft-mozleywilliams-dnsop-dnsaid/)** (score: 3.6) — Uses existing DNS infrastructure for AI agent discovery through structured namespace and metadata ex - **[draft-eggert-mailmaint-uaautoconf](https://datatracker.ietf.org/doc/draft-eggert-mailmaint-uaautoconf/)** (score: 3.6) — Specifies automatic configuration mechanism for email, calendar, and contact applications. Enables s - **[draft-gaikwad-aps-profile](https://datatracker.ietf.org/doc/draft-gaikwad-aps-profile/)** (score: 3.6) — Storage service profile for agent persistent state including embeddings, preferences, and audit logs - **[draft-moreno-lisp-uberlay](https://datatracker.ietf.org/doc/draft-moreno-lisp-uberlay/)** (score: 3.6) — Describes using LISP to interconnect multiple independent network overlays through a transit overlay - **[draft-ietf-lake-edhoc-psk](https://datatracker.ietf.org/doc/draft-ietf-lake-edhoc-psk/)** (score: 3.6) — Specifies pre-shared key authentication method for EDHOC key exchange protocol. Enhances efficiency - **[draft-vaughan-aipref-vocab](https://datatracker.ietf.org/doc/draft-vaughan-aipref-vocab/)** (score: 3.6) — Proposes vocabulary for rightsholders to express content preferences for AI training use through met - **[draft-irtf-nmrg-llm-nm](https://datatracker.ietf.org/doc/draft-irtf-nmrg-llm-nm/)** (score: 3.5) — Defines framework for collaborative network management between LLMs and human operators with human-i - **[draft-ietf-sml-trust](https://datatracker.ietf.org/doc/draft-ietf-sml-trust/)** (score: 3.5) — Provides trust and security recommendations for handling structured data in email messages. Addresse - **[draft-zeng-opsawg-applicability-mcp-a2a](https://datatracker.ietf.org/doc/draft-zeng-opsawg-applicability-mcp-a2a/)** (score: 3.5) — Analyzes NETCONF limitations for advanced scenarios and proposes MCP and A2A protocols as complement - **[draft-kartha-grd](https://datatracker.ietf.org/doc/draft-kartha-grd/)** (score: 3.4) — Defines architectural framework for discovering network resources based on physical location and con - **[draft-li-cats-aisemantic-contract](https://datatracker.ietf.org/doc/draft-li-cats-aisemantic-contract/)** (score: 3.4) — Defines a contract mechanism allowing AI applications to communicate semantic information about thei - **[draft-kartha-internet20-ainative](https://datatracker.ietf.org/doc/draft-kartha-internet20-ainative/)** (score: 3.4) — Proposes Internet 2.0 architecture with AI models as first-class network entities, including HTTP+AI - **[draft-yan-a2a-device-agent-applicability](https://datatracker.ietf.org/doc/draft-yan-a2a-device-agent-applicability/)** (score: 3.4) — Discusses applying Agent-to-Agent (A2A) Protocol to network management for communication between Con - **[draft-ietf-lamps-private-key-stmt-attr](https://datatracker.ietf.org/doc/draft-ietf-lamps-private-key-stmt-attr/)** (score: 3.4) — Defines X.509 attribute for private key possession statements as alternative to cryptographic proof - **[draft-yue-moq-transporting-sensing-data](https://datatracker.ietf.org/doc/draft-yue-moq-transporting-sensing-data/)** (score: 3.4) — Proposes using Media Over QUIC (MOQ) to transport large-scale, real-time sensing data in 6G networks - **[draft-ramakrishna-satp-views-addresses](https://datatracker.ietf.org/doc/draft-ramakrishna-satp-views-addresses/)** (score: 3.4) — Defines view and addressing mechanisms for secure asset transfer between DLT systems. Enables cross- - **[draft-zw-rtgwg-mcp-network-mgmt](https://datatracker.ietf.org/doc/draft-zw-rtgwg-mcp-network-mgmt/)** (score: 3.4) — Specifies MCP extensions for network equipment management with routers/switches as MCP servers. Defi - **[draft-thomson-aipref-sup](https://datatracker.ietf.org/doc/draft-thomson-aipref-sup/)** (score: 3.4) — Defines simple format for content usage preference expressions with HTTP header field. Updates RFC93 - **[draft-stephan-ai-agent-6g](https://datatracker.ietf.org/doc/draft-stephan-ai-agent-6g/)** (score: 3.4) — Examines AI agent communication protocols specifically for 6G systems based on 3GPP requirements. Ex - **[draft-han-rtgwg-codeployment-pfc-fgfc](https://datatracker.ietf.org/doc/draft-han-rtgwg-codeployment-pfc-fgfc/)** (score: 3.4) — Describes use cases for coordinating flow control between data center PFC and WAN fine-grained flow - **[draft-sz-dmsc-iaip](https://datatracker.ietf.org/doc/draft-sz-dmsc-iaip/)** (score: 3.3) — Defines Intent-based Agent Interconnection Protocol (IAIP) for dynamic agent discovery and routing a - **[draft-xsaopig-nmop-service-flow-modal-mapping](https://datatracker.ietf.org/doc/draft-xsaopig-nmop-service-flow-modal-mapping/)** (score: 3.3) — Proposes a framework using ALTO protocol and SDN architecture for mapping service flow characteristi - **[draft-mcp-over-moqt](https://datatracker.ietf.org/doc/draft-mcp-over-moqt/)** (score: 3.3) — Defines transport mapping for Model Context Protocol over Media over QUIC Transport. Specifies how M - **[draft-jennings-mcp-over-moqt](https://datatracker.ietf.org/doc/draft-jennings-mcp-over-moqt/)** (score: 3.3) — Defines transport mapping for Model Context Protocol over Media over QUIC Transport. Specifies how M - **[draft-chuyi-nmrg-ai-agent-network](https://datatracker.ietf.org/doc/draft-chuyi-nmrg-ai-agent-network/)** (score: 3.2) — Focuses on large language model-based agents for network operations and maintenance. Addresses pract - **[draft-liu-rtgwg-agent-gateway-requirements](https://datatracker.ietf.org/doc/draft-liu-rtgwg-agent-gateway-requirements/)** (score: 3.2) — Discusses requirements for Agent Gateways in agent-to-agent communications to improve scalability, e - **[draft-gaikwad-woa](https://datatracker.ietf.org/doc/draft-gaikwad-woa/)** (score: 3.2) — Specifies Web of Agents (WoA) format using JSON Schema to describe AI agent inputs/outputs served fr ## Human-agent interaction (19 drafts) - **[draft-drake-email-tpm-attestation](https://datatracker.ietf.org/doc/draft-drake-email-tpm-attestation/)** (score: 4.6) — Defines hardware attestation for email using TPM verification chains to prevent spam and provide Syb - **[draft-ietf-aipref-vocab](https://datatracker.ietf.org/doc/draft-ietf-aipref-vocab/)** (score: 4.4) — Defines a standardized vocabulary for expressing preferences about how digital assets should be used - **[draft-dhir-http-agent-profile](https://datatracker.ietf.org/doc/draft-dhir-http-agent-profile/)** (score: 4.2) — Defines HTTP Agent Profile for authenticating agent traffic, separating human from agent traffic, an - **[draft-song-tsvwg-camp](https://datatracker.ietf.org/doc/draft-song-tsvwg-camp/)** (score: 4.2) — Proposes CAMP, a multipath transport protocol for interactive multimodal LLM systems that maintains - **[draft-liu-agent-operation-authorization](https://datatracker.ietf.org/doc/draft-liu-agent-operation-authorization/)** (score: 4.1) — Specifies framework for verifiable delegation of actions from humans to AI agents using JWT tokens. - **[draft-cui-nmrg-llm-nm](https://datatracker.ietf.org/doc/draft-cui-nmrg-llm-nm/)** (score: 4.1) — Defines framework for collaborative network management between LLM agents and human operators. Intro - **[draft-steele-agent-considerations](https://datatracker.ietf.org/doc/draft-steele-agent-considerations/)** (score: 4.0) — Defines guidelines for IETF specifications to support AI agent consumption and code generation. Intr - **[draft-mishra-oauth-agent-grants](https://datatracker.ietf.org/doc/draft-mishra-oauth-agent-grants/)** (score: 4.0) — Extends OAuth 2.0 for AI agent authorization with human consent verification, revocation, and audit - **[draft-rosenberg-aiproto-cheq](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-cheq/)** (score: 3.9) — Proposes CHEQ protocol for human confirmation of AI agent decisions before execution. Protects again - **[draft-farzdusa-aipref-enduser](https://datatracker.ietf.org/doc/draft-farzdusa-aipref-enduser/)** (score: 3.8) — Documents potential end user impacts of AI preference signaling standards across technological, lega - **[draft-oauth-ai-agents-on-behalf-of-user](https://datatracker.ietf.org/doc/draft-oauth-ai-agents-on-behalf-of-user/)** (score: 3.7) — This draft extends OAuth 2.0 to enable AI agents to securely obtain access tokens for acting on beha - **[draft-rosenberg-cheq](https://datatracker.ietf.org/doc/draft-rosenberg-cheq/)** (score: 3.6) — Proposes CHEQ protocol for human-in-the-loop confirmation of AI agent decisions before execution. Us - **[draft-zm-rtgwg-mcp-troubleshooting](https://datatracker.ietf.org/doc/draft-zm-rtgwg-mcp-troubleshooting/)** (score: 3.6) — Proposes using Model Context Protocol (MCP) to enable LLM-based automated network troubleshooting. M - **[draft-altanai-aipref-realtime-protocol-bindings](https://datatracker.ietf.org/doc/draft-altanai-aipref-realtime-protocol-bindings/)** (score: 3.6) — Defines how AI preference expressions are bound to real-time protocols like SIP and SDP. Specifies h - **[draft-irtf-nmrg-llm-nm](https://datatracker.ietf.org/doc/draft-irtf-nmrg-llm-nm/)** (score: 3.5) — Defines framework for collaborative network management between LLMs and human operators with human-i - **[draft-zeng-mcp-network-measurement](https://datatracker.ietf.org/doc/draft-zeng-mcp-network-measurement/)** (score: 3.5) — Proposes MCP framework for intelligent network measurement with AI assistance. Enables natural langu - **[draft-meta-layer-overview](https://datatracker.ietf.org/doc/draft-meta-layer-overview/)** (score: 3.5) — Introduces Meta-layer concept as coordination substrate for presence, annotation, and governance on - **[draft-thomson-aipref-sup](https://datatracker.ietf.org/doc/draft-thomson-aipref-sup/)** (score: 3.4) — Defines simple format for content usage preference expressions with HTTP header field. Updates RFC93 - **[draft-zeng-nmrg-mcp-usecases-requirements](https://datatracker.ietf.org/doc/draft-zeng-nmrg-mcp-usecases-requirements/)** (score: 3.4) — Presents problem statement for integrating Model Context Protocol into network management for AI age ## Identity / authentication for AI agents (6 drafts) - **[draft-nandakumar-agent-sd-jwt](https://datatracker.ietf.org/doc/draft-nandakumar-agent-sd-jwt/)** (score: 3.9) — This draft defines SD-Card, a Selective Disclosure JWT encoding of Agent Cards that enables privacy- - **[draft-wahl-scim-agent-schema](https://datatracker.ietf.org/doc/draft-wahl-scim-agent-schema/)** (score: 3.9) — This draft extends the SCIM (System for Cross-domain Identity Management) protocol to support AI age - **[draft-oauth-ai-agents-on-behalf-of-user](https://datatracker.ietf.org/doc/draft-oauth-ai-agents-on-behalf-of-user/)** (score: 3.7) — This draft extends OAuth 2.0 to enable AI agents to securely obtain access tokens for acting on beha - **[draft-chen-agent-decoupled-authorization-model](https://datatracker.ietf.org/doc/draft-chen-agent-decoupled-authorization-model/)** (score: 3.5) — This draft proposes a decoupled authorization framework for AI agents that enables dynamic, intent-b - **[draft-huang-acme-scalable-agent-enrollment](https://datatracker.ietf.org/doc/draft-huang-acme-scalable-agent-enrollment/)** (score: 3.5) — This draft proposes two scalable models for certificate enrollment of AI agents: one using Zero-Know - **[draft-zheng-dispatch-agent-identity-management](https://datatracker.ietf.org/doc/draft-zheng-dispatch-agent-identity-management/)** (score: 3.3) — This draft proposes an identity management framework for agents in an Internet of Agents (IOA) syste ## ML traffic mgmt (30 drafts) - **[draft-calabria-bmwg-ai-fabric-inference-bench](https://datatracker.ietf.org/doc/draft-calabria-bmwg-ai-fabric-inference-bench/)** (score: 4.5) — Defines benchmarking methodology for AI inference network fabrics. Establishes KPIs and test procedu - **[draft-dhir-http-agent-profile](https://datatracker.ietf.org/doc/draft-dhir-http-agent-profile/)** (score: 4.2) — Defines HTTP Agent Profile for authenticating agent traffic, separating human from agent traffic, an - **[draft-calabria-bmwg-ai-fabric-terminology](https://datatracker.ietf.org/doc/draft-calabria-bmwg-ai-fabric-terminology/)** (score: 4.2) — Defines comprehensive benchmarking terminology for AI network fabrics including collective communica - **[draft-li-spring-rdma-multicast-over-srv6](https://datatracker.ietf.org/doc/draft-li-spring-rdma-multicast-over-srv6/)** (score: 4.2) — Specifies SRv6 extensions for RDMA multicast delivery with new End.MT behavior and ACK/NACK aggregat - **[draft-song-tsvwg-camp](https://datatracker.ietf.org/doc/draft-song-tsvwg-camp/)** (score: 4.2) — Proposes CAMP, a multipath transport protocol for interactive multimodal LLM systems that maintains - **[draft-yao-tsvwg-cco-requirement-and-analysis](https://datatracker.ietf.org/doc/draft-yao-tsvwg-cco-requirement-and-analysis/)** (score: 4.2) — Analyzes collective communication optimizations for AI training and inference clusters built on RDMA - **[draft-cui-nmrg-llm-nm](https://datatracker.ietf.org/doc/draft-cui-nmrg-llm-nm/)** (score: 4.1) — Defines framework for collaborative network management between LLM agents and human operators. Intro - **[draft-chen-nmrg-semantic-inference-routing](https://datatracker.ietf.org/doc/draft-chen-nmrg-semantic-inference-routing/)** (score: 4.1) — Defines SIRP protocol for content-aware routing of AI inference requests. Enables routing decisions - **[draft-dunbar-neotec-ac-te-applicability](https://datatracker.ietf.org/doc/draft-dunbar-neotec-ac-te-applicability/)** (score: 4.0) — Applies existing IETF YANG models for Attachment Circuits and Traffic Engineering to dynamic AI mode - **[draft-liao-aipref-autoctl-core](https://datatracker.ietf.org/doc/draft-liao-aipref-autoctl-core/)** (score: 4.0) — Defines core machine-readable protocol for server-side automation permissions targeting AI-driven we - **[draft-zhang-rtgwg-multicast-requirements-gaps-aidc](https://datatracker.ietf.org/doc/draft-zhang-rtgwg-multicast-requirements-gaps-aidc/)** (score: 3.9) — Identifies requirements for multicast technology in AI Data Centers to improve efficiency of point-t - **[draft-akhavain-moussa-ai-network](https://datatracker.ietf.org/doc/draft-akhavain-moussa-ai-network/)** (score: 3.9) — Proposes Data and Agent Aware-Inference and Training Network (DA-ITN) architecture. Comprehensive mu - **[draft-pan-tsvwg-pie](https://datatracker.ietf.org/doc/draft-pan-tsvwg-pie/)** (score: 3.9) — Presents PIE queue management algorithm to address bufferbloat by controlling queueing latency. Ligh - **[draft-jurkovikj-httpapi-agentic-state](https://datatracker.ietf.org/doc/draft-jurkovikj-httpapi-agentic-state/)** (score: 3.9) — Defines Agentic State Transfer (AST) HTTP profile for managing canonical resource state across multi - **[draft-yuan-rtgwg-traffic-agent-usecase](https://datatracker.ietf.org/doc/draft-yuan-rtgwg-traffic-agent-usecase/)** (score: 3.7) — Presents use cases for AI agents optimizing network traffic through dynamic resource adjustment. Det - **[draft-an-nmrg-i2icf-cits](https://datatracker.ietf.org/doc/draft-an-nmrg-i2icf-cits/)** (score: 3.7) — Defines framework for orchestrating In-Network Computing Functions in Cooperative Intelligent Transp - **[draft-cui-nmrg-auto-test](https://datatracker.ietf.org/doc/draft-cui-nmrg-auto-test/)** (score: 3.6) — Framework for AI-assisted network protocol testing using LLMs and automated test generation. Defines - **[draft-xsaopig-nsttlp-traffic-labeling](https://datatracker.ietf.org/doc/draft-xsaopig-nsttlp-traffic-labeling/)** (score: 3.6) — Specifies protocol for embedding service type identifiers in network packets to enable intelligent t - **[draft-zeng-mcp-network-measurement](https://datatracker.ietf.org/doc/draft-zeng-mcp-network-measurement/)** (score: 3.5) — Proposes MCP framework for intelligent network measurement with AI assistance. Enables natural langu - **[draft-templin-intarea-aero](https://datatracker.ietf.org/doc/draft-templin-intarea-aero/)** (score: 3.5) — Specifies Automatic Extended Route Optimization (AERO) service for IP internetworking over Overlay M - **[draft-du-catalist-routing-considerations](https://datatracker.ietf.org/doc/draft-du-catalist-routing-considerations/)** (score: 3.4) — Proposes routing considerations for AI agent-to-agent communication in overlay networks. Focuses on - **[draft-tan-ccamp-uonaco-problem-statement](https://datatracker.ietf.org/doc/draft-tan-ccamp-uonaco-problem-statement/)** (score: 3.4) — Defines requirements for unified orchestration between optical networks and AI computing to enable c - **[draft-li-cats-aisemantic-contract](https://datatracker.ietf.org/doc/draft-li-cats-aisemantic-contract/)** (score: 3.4) — Defines a contract mechanism allowing AI applications to communicate semantic information about thei - **[draft-yue-moq-transporting-sensing-data](https://datatracker.ietf.org/doc/draft-yue-moq-transporting-sensing-data/)** (score: 3.4) — Proposes using Media Over QUIC (MOQ) to transport large-scale, real-time sensing data in 6G networks - **[draft-han-rtgwg-codeployment-pfc-fgfc](https://datatracker.ietf.org/doc/draft-han-rtgwg-codeployment-pfc-fgfc/)** (score: 3.4) — Describes use cases for coordinating flow control between data center PFC and WAN fine-grained flow - **[draft-wang-cats-innetwork-infer](https://datatracker.ietf.org/doc/draft-wang-cats-innetwork-infer/)** (score: 3.3) — Proposes a framework for decentralized LLM inference across untrusted participants using layer-aware - **[draft-xsaopig-nmop-service-flow-modal-mapping](https://datatracker.ietf.org/doc/draft-xsaopig-nmop-service-flow-modal-mapping/)** (score: 3.3) — Proposes a framework using ALTO protocol and SDN architecture for mapping service flow characteristi - **[draft-bernardos-nmrg-agentic-network-optimization](https://datatracker.ietf.org/doc/draft-bernardos-nmrg-agentic-network-optimization/)** (score: 3.3) — Focuses on agentic AI for distributed sensing in ISAC networks with joint optimization of sensing an - **[draft-chuyi-nmrg-ai-agent-network](https://datatracker.ietf.org/doc/draft-chuyi-nmrg-ai-agent-network/)** (score: 3.2) — Focuses on large language model-based agents for network operations and maintenance. Addresses pract - **[draft-zhao-detnet-enhanced-use-cases](https://datatracker.ietf.org/doc/draft-zhao-detnet-enhanced-use-cases/)** (score: 3.2) — Describes enhanced use cases for scaling deterministic networks beyond RFC8578, covering industrial ## Model serving/inference (22 drafts) - **[draft-williams-netmod-lm-hierarchy-topology](https://datatracker.ietf.org/doc/draft-williams-netmod-lm-hierarchy-topology/)** (score: 4.6) — Defines YANG data model for hierarchical language model coordination across tiny, small, and large L - **[draft-chang-agent-token-efficient](https://datatracker.ietf.org/doc/draft-chang-agent-token-efficient/)** (score: 4.5) — Defines ADOL (Agentic Data Optimization Layer) to address token bloat in agent communication protoco - **[draft-calabria-bmwg-ai-fabric-inference-bench](https://datatracker.ietf.org/doc/draft-calabria-bmwg-ai-fabric-inference-bench/)** (score: 4.5) — Defines benchmarking methodology for AI inference network fabrics. Establishes KPIs and test procedu - **[draft-wang-cats-odsi](https://datatracker.ietf.org/doc/draft-wang-cats-odsi/)** (score: 4.5) — Specifies framework for decentralized LLM inference across untrusted participants with layer-aware e - **[draft-wmz-nmrg-agent-ndt-arch](https://datatracker.ietf.org/doc/draft-wmz-nmrg-agent-ndt-arch/)** (score: 4.2) — Comprehensive architecture combining Network Digital Twin with Agentic AI for intent-based network o - **[draft-gaikwad-llm-benchmarking-methodology](https://datatracker.ietf.org/doc/draft-gaikwad-llm-benchmarking-methodology/)** (score: 4.2) — Defines comprehensive benchmarking methodologies for LLM inference serving systems including test pr - **[draft-gaikwad-llm-benchmarking-profiles](https://datatracker.ietf.org/doc/draft-gaikwad-llm-benchmarking-profiles/)** (score: 4.2) — Defines performance benchmarking profiles binding terminology and methodology to concrete architectu - **[draft-yao-tsvwg-cco-requirement-and-analysis](https://datatracker.ietf.org/doc/draft-yao-tsvwg-cco-requirement-and-analysis/)** (score: 4.2) — Analyzes collective communication optimizations for AI training and inference clusters built on RDMA - **[draft-chen-nmrg-semantic-inference-routing](https://datatracker.ietf.org/doc/draft-chen-nmrg-semantic-inference-routing/)** (score: 4.1) — Defines SIRP protocol for content-aware routing of AI inference requests. Enables routing decisions - **[draft-chen-nmrg-multi-provider-inference-api](https://datatracker.ietf.org/doc/draft-chen-nmrg-multi-provider-inference-api/)** (score: 4.0) — Specifies extensions for multi-provider AI inference using OpenAI API as reference standard. Enables - **[draft-jennings-ai-mcp-over-moq](https://datatracker.ietf.org/doc/draft-jennings-ai-mcp-over-moq/)** (score: 4.0) — Defines how to transport Model Context Protocol (MCP) messages over Media over QUIC Transport (MOQT) - **[draft-dunbar-neotec-ac-te-applicability](https://datatracker.ietf.org/doc/draft-dunbar-neotec-ac-te-applicability/)** (score: 4.0) — Applies existing IETF YANG models for Attachment Circuits and Traffic Engineering to dynamic AI mode - **[draft-zhang-rtgwg-multicast-requirements-gaps-aidc](https://datatracker.ietf.org/doc/draft-zhang-rtgwg-multicast-requirements-gaps-aidc/)** (score: 3.9) — Identifies requirements for multicast technology in AI Data Centers to improve efficiency of point-t - **[draft-akhavain-moussa-ai-network](https://datatracker.ietf.org/doc/draft-akhavain-moussa-ai-network/)** (score: 3.9) — Proposes Data and Agent Aware-Inference and Training Network (DA-ITN) architecture. Comprehensive mu - **[draft-tsyrulnikov-rats-attested-inference-receipt](https://datatracker.ietf.org/doc/draft-tsyrulnikov-rats-attested-inference-receipt/)** (score: 3.9) — Defines Attested Inference Receipt (AIR) using COSE/CWT to create verifiable receipts for confidenti - **[draft-li-individual-inip](https://datatracker.ietf.org/doc/draft-li-individual-inip/)** (score: 3.8) — Specifies a protocol for performing lightweight ML inference directly in network devices like switch - **[draft-sogomonian-aiip-architecture](https://datatracker.ietf.org/doc/draft-sogomonian-aiip-architecture/)** (score: 3.7) — Defines architectural model for Artificial Intelligence Internet Protocol (AIIP) enabling stateless, - **[draft-li-cats-idn](https://datatracker.ietf.org/doc/draft-li-cats-idn/)** (score: 3.6) — Introduces Intelligence Delivery Network (IDN) framework for deploying ML models across distributed - **[draft-kartha-internet20-ainative](https://datatracker.ietf.org/doc/draft-kartha-internet20-ainative/)** (score: 3.4) — Proposes Internet 2.0 architecture with AI models as first-class network entities, including HTTP+AI - **[draft-zhu-anima-service-intent](https://datatracker.ietf.org/doc/draft-zhu-anima-service-intent/)** (score: 3.4) — Defines a structured semantic model for expressing service-level objectives and constraints across n - **[draft-wang-cats-innetwork-infer](https://datatracker.ietf.org/doc/draft-wang-cats-innetwork-infer/)** (score: 3.3) — Proposes a framework for decentralized LLM inference across untrusted participants using layer-aware - **[draft-chuyi-nmrg-ai-agent-network](https://datatracker.ietf.org/doc/draft-chuyi-nmrg-ai-agent-network/)** (score: 3.2) — Focuses on large language model-based agents for network operations and maintenance. Addresses pract ## Other AI/agent (8 drafts) - **[draft-calabria-bmwg-ai-fabric-inference-bench](https://datatracker.ietf.org/doc/draft-calabria-bmwg-ai-fabric-inference-bench/)** (score: 4.5) — Defines benchmarking methodology for AI inference network fabrics. Establishes KPIs and test procedu - **[draft-ietf-tls-ecdhe-mlkem](https://datatracker.ietf.org/doc/draft-ietf-tls-ecdhe-mlkem/)** (score: 4.4) — Defines hybrid post-quantum key agreement mechanisms for TLS 1.3 that combine ML-KEM with traditiona - **[draft-wmz-nmrg-agent-ndt-arch](https://datatracker.ietf.org/doc/draft-wmz-nmrg-agent-ndt-arch/)** (score: 4.2) — Comprehensive architecture combining Network Digital Twin with Agentic AI for intent-based network o - **[draft-an-nmrg-i2icf-cits](https://datatracker.ietf.org/doc/draft-an-nmrg-i2icf-cits/)** (score: 3.7) — Defines framework for orchestrating In-Network Computing Functions in Cooperative Intelligent Transp - **[draft-cui-nmrg-auto-test](https://datatracker.ietf.org/doc/draft-cui-nmrg-auto-test/)** (score: 3.6) — Framework for AI-assisted network protocol testing using LLMs and automated test generation. Defines - **[draft-stephan-ai-agent-6g](https://datatracker.ietf.org/doc/draft-stephan-ai-agent-6g/)** (score: 3.4) — Examines AI agent communication protocols specifically for 6G systems based on 3GPP requirements. Ex - **[draft-khatri-sipcore-call-transfer-fail-response](https://datatracker.ietf.org/doc/draft-khatri-sipcore-call-transfer-fail-response/)** (score: 3.3) — Defines a new SIP response code (497) for indicating call transfer failures with optional granular w - **[draft-bernardos-nmrg-agentic-network-optimization](https://datatracker.ietf.org/doc/draft-bernardos-nmrg-agentic-network-optimization/)** (score: 3.3) — Focuses on agentic AI for distributed sensing in ISAC networks with joint optimization of sensing an ## Policy / governance / ethical frameworks (1 drafts) - **[draft-chen-agent-decoupled-authorization-model](https://datatracker.ietf.org/doc/draft-chen-agent-decoupled-authorization-model/)** (score: 3.5) — This draft proposes a decoupled authorization framework for AI agents that enables dynamic, intent-b ## Policy/governance (63 drafts) - **[draft-cowles-volt](https://datatracker.ietf.org/doc/draft-cowles-volt/)** (score: 4.8) — Defines tamper-evident execution trace format for AI agent workflows using hash chains and cryptogra - **[draft-aylward-daap-v2](https://datatracker.ietf.org/doc/draft-aylward-daap-v2/)** (score: 4.8) — Defines comprehensive protocol for AI agent accountability including authentication, monitoring, and - **[draft-goswami-agentic-jwt](https://datatracker.ietf.org/doc/draft-goswami-agentic-jwt/)** (score: 4.5) — Extends OAuth 2.0 with Agentic JWT to address authorization challenges in autonomous AI systems. Int - **[draft-wang-cats-odsi](https://datatracker.ietf.org/doc/draft-wang-cats-odsi/)** (score: 4.5) — Specifies framework for decentralized LLM inference across untrusted participants with layer-aware e - **[draft-birkholz-verifiable-agent-conversations](https://datatracker.ietf.org/doc/draft-birkholz-verifiable-agent-conversations/)** (score: 4.5) — Defines CDDL-based data format for verifiable agent conversation records using COSE signing. Support - **[draft-aylward-aiga-2](https://datatracker.ietf.org/doc/draft-aylward-aiga-2/)** (score: 4.5) — Comprehensive AI governance framework with tiered risk model, federated authority network, and econo - **[draft-ietf-aipref-vocab](https://datatracker.ietf.org/doc/draft-ietf-aipref-vocab/)** (score: 4.4) — Defines a standardized vocabulary for expressing preferences about how digital assets should be used - **[draft-cui-nmrg-llm-benchmark](https://datatracker.ietf.org/doc/draft-cui-nmrg-llm-benchmark/)** (score: 4.3) — Provides comprehensive evaluation framework for LLM-based network configuration agents. Includes emu - **[draft-mw-wimse-transitive-attestation](https://datatracker.ietf.org/doc/draft-mw-wimse-transitive-attestation/)** (score: 4.3) — Defines WIMSE profile for cryptographically binding workload identities to their execution environme - **[draft-wmz-nmrg-agent-ndt-arch](https://datatracker.ietf.org/doc/draft-wmz-nmrg-agent-ndt-arch/)** (score: 4.2) — Comprehensive architecture combining Network Digital Twin with Agentic AI for intent-based network o - **[draft-dhir-http-agent-profile](https://datatracker.ietf.org/doc/draft-dhir-http-agent-profile/)** (score: 4.2) — Defines HTTP Agent Profile for authenticating agent traffic, separating human from agent traffic, an - **[draft-chen-oauth-rar-agent-extensions](https://datatracker.ietf.org/doc/draft-chen-oauth-rar-agent-extensions/)** (score: 4.2) — Extends OAuth RAR with policy_context and lifecycle_binding members for AI agent environments. Enabl - **[draft-aylward-aiga-1](https://datatracker.ietf.org/doc/draft-aylward-aiga-1/)** (score: 4.2) — Specifies AI Governance and Accountability Protocol with tiered risk-based governance model. Include - **[draft-aap-oauth-profile](https://datatracker.ietf.org/doc/draft-aap-oauth-profile/)** (score: 4.2) — Defines an OAuth 2.0 authorization profile specifically for autonomous AI agents, extending existing - **[draft-oauth-transaction-tokens-for-agents](https://datatracker.ietf.org/doc/draft-oauth-transaction-tokens-for-agents/)** (score: 4.2) — Extends OAuth Transaction Tokens framework to support agent context propagation with actor and princ - **[draft-jewell-aibdp](https://datatracker.ietf.org/doc/draft-jewell-aibdp/)** (score: 4.2) — Defines AI Boundary Declaration Protocol for expressing content usage boundaries for AI systems. Pro - **[draft-liu-agent-operation-authorization](https://datatracker.ietf.org/doc/draft-liu-agent-operation-authorization/)** (score: 4.1) — Specifies framework for verifiable delegation of actions from humans to AI agents using JWT tokens. - **[draft-yue-anima-agent-recovery-networks](https://datatracker.ietf.org/doc/draft-yue-anima-agent-recovery-networks/)** (score: 4.1) — Defines task-oriented multi-agent framework for fault recovery in converged mobile networks. Targets - **[draft-schulze-ecap](https://datatracker.ietf.org/doc/draft-schulze-ecap/)** (score: 4.1) — ECAP defines a cryptographically-verified protocol for web crawlers to obtain consent from hosts bef - **[draft-jadoon-nmrg-agentic-ai-autonomous-networks](https://datatracker.ietf.org/doc/draft-jadoon-nmrg-agentic-ai-autonomous-networks/)** (score: 4.1) — Introduces architectural principles for integrating AI agents into IP protocol stack layers while pr - **[draft-steele-agent-considerations](https://datatracker.ietf.org/doc/draft-steele-agent-considerations/)** (score: 4.0) — Defines guidelines for IETF specifications to support AI agent consumption and code generation. Intr - **[draft-chen-nmrg-multi-provider-inference-api](https://datatracker.ietf.org/doc/draft-chen-nmrg-multi-provider-inference-api/)** (score: 4.0) — Specifies extensions for multi-provider AI inference using OpenAI API as reference standard. Enables - **[draft-mishra-oauth-agent-grants](https://datatracker.ietf.org/doc/draft-mishra-oauth-agent-grants/)** (score: 4.0) — Extends OAuth 2.0 for AI agent authorization with human consent verification, revocation, and audit - **[draft-barney-caam](https://datatracker.ietf.org/doc/draft-barney-caam/)** (score: 4.0) — Specifies Contextual Agent Authorization Mesh for runtime authorization of agents after discovery, p - **[draft-nennemann-wimse-ect](https://datatracker.ietf.org/doc/draft-nennemann-wimse-ect/)** (score: 4.0) — Defines Execution Context Tokens as JWT extension to WIMSE for tracking task execution in distribute - **[draft-liao-aipref-autoctl-core](https://datatracker.ietf.org/doc/draft-liao-aipref-autoctl-core/)** (score: 4.0) — Defines core machine-readable protocol for server-side automation permissions targeting AI-driven we - **[draft-berlinai-vera](https://datatracker.ietf.org/doc/draft-berlinai-vera/)** (score: 3.9) — Introduces VERA, a zero-trust architecture for AI agent security with five enforcement pillars and c - **[draft-ietf-tls-deprecate-obsolete-kex](https://datatracker.ietf.org/doc/draft-ietf-tls-deprecate-obsolete-kex/)** (score: 3.8) — Deprecates obsolete key exchange methods in TLS 1.2 including finite field DH and RSA. Updates multi - **[draft-srijal-agents-policy](https://datatracker.ietf.org/doc/draft-srijal-agents-policy/)** (score: 3.8) — Specifies AGENTS.TXT protocol as strict plaintext policy file for automated clients, bots, and crawl - **[draft-zhao-nmop-network-management-agent](https://datatracker.ietf.org/doc/draft-zhao-nmop-network-management-agent/)** (score: 3.8) — Defines AI-driven Network Management Agent concept for Level 4 autonomous networks. Specifies integr - **[draft-ietf-aipref-attach](https://datatracker.ietf.org/doc/draft-ietf-aipref-attach/)** (score: 3.8) — Specifies how AI usage preferences can be signaled during HTTP content acquisition. Updates RFC 9309 - **[draft-farzdusa-aipref-enduser](https://datatracker.ietf.org/doc/draft-farzdusa-aipref-enduser/)** (score: 3.8) — Documents potential end user impacts of AI preference signaling standards across technological, lega - **[draft-scim-agent-extension](https://datatracker.ietf.org/doc/draft-scim-agent-extension/)** (score: 3.7) — Extends SCIM 2.0 specification to manage agents and agentic applications across domains. Builds on e - **[draft-rosenberg-aiproto-framework](https://datatracker.ietf.org/doc/draft-rosenberg-aiproto-framework/)** (score: 3.7) — Provides framework and requirements for AI agent protocols on the Internet. Surveys existing approac - **[draft-melnikov-sasl2](https://datatracker.ietf.org/doc/draft-melnikov-sasl2/)** (score: 3.7) — Updates SASL framework to support modern authentication requirements including multi-factor authenti - **[draft-ietf-lake-ra](https://datatracker.ietf.org/doc/draft-ietf-lake-ra/)** (score: 3.7) — Specifies remote attestation procedures integrated with EDHOC lightweight key exchange protocol. Ena - **[draft-ietf-lamps-rfc7030-csrattrs](https://datatracker.ietf.org/doc/draft-ietf-lamps-rfc7030-csrattrs/)** (score: 3.7) — Updates RFC7030 to clarify CSR Attributes Response encoding and adds template-based approach for EST - **[draft-gaikwad-south-authorization](https://datatracker.ietf.org/doc/draft-gaikwad-south-authorization/)** (score: 3.7) — Authorization protocol supporting probabilistic decisions for agents and services. Enables uncertain - **[draft-kotecha-agentic-dispute-protocol](https://datatracker.ietf.org/doc/draft-kotecha-agentic-dispute-protocol/)** (score: 3.6) — Defines a protocol for autonomous agents to file and resolve disputes through structured automated p - **[draft-vandoulas-aidp](https://datatracker.ietf.org/doc/draft-vandoulas-aidp/)** (score: 3.6) — Defines a comprehensive control-plane protocol for secure agent interactions with delegation, author - **[draft-messous-eat-ai](https://datatracker.ietf.org/doc/draft-messous-eat-ai/)** (score: 3.6) — Defines an Entity Attestation Token profile for remote attestation of autonomous AI agents, specifyi - **[draft-reilly-sentinel-protocol](https://datatracker.ietf.org/doc/draft-reilly-sentinel-protocol/)** (score: 3.6) — Defines blockchain-anchored integrity protocol for AI lifecycle provenance using Sentinel Evidence P - **[draft-xsaopig-nsttlp-traffic-labeling](https://datatracker.ietf.org/doc/draft-xsaopig-nsttlp-traffic-labeling/)** (score: 3.6) — Specifies protocol for embedding service type identifiers in network packets to enable intelligent t - **[draft-gaikwad-aps-profile](https://datatracker.ietf.org/doc/draft-gaikwad-aps-profile/)** (score: 3.6) — Storage service profile for agent persistent state including embeddings, preferences, and audit logs - **[draft-pbs-sidrops-roaanycast](https://datatracker.ietf.org/doc/draft-pbs-sidrops-roaanycast/)** (score: 3.6) — Defines best practices for managing Route Origin Authorizations (ROAs) for globally anycasted servic - **[draft-vaughan-aipref-vocab](https://datatracker.ietf.org/doc/draft-vaughan-aipref-vocab/)** (score: 3.6) — Proposes vocabulary for rightsholders to express content preferences for AI training use through met - **[draft-song-oauth-ai-agent-collaborate-authz](https://datatracker.ietf.org/doc/draft-song-oauth-ai-agent-collaborate-authz/)** (score: 3.5) — Proposes OAuth 2.0 extension for multi-AI agent collaboration with applier-on-behalf-of authorizatio - **[draft-wang-hjs-accountability](https://datatracker.ietf.org/doc/draft-wang-hjs-accountability/)** (score: 3.5) — Defines HJS accountability layer for AI agents using blockchain-anchored timestamps to create immuta - **[draft-ahn-nmrg-5g-security-i2nsf-framework](https://datatracker.ietf.org/doc/draft-ahn-nmrg-5g-security-i2nsf-framework/)** (score: 3.5) — Presents integrated framework for automated 5G edge network security using I2NSF architecture and In - **[draft-jia-oauth-scope-aggregation](https://datatracker.ietf.org/doc/draft-jia-oauth-scope-aggregation/)** (score: 3.5) — Extends OAuth 2.0 with scope aggregation to reduce authorization round-trips in multi-step AI agent - **[draft-meta-layer-overview](https://datatracker.ietf.org/doc/draft-meta-layer-overview/)** (score: 3.5) — Introduces Meta-layer concept as coordination substrate for presence, annotation, and governance on - **[draft-yuan-rtgwg-security-agent-usecase](https://datatracker.ietf.org/doc/draft-yuan-rtgwg-security-agent-usecase/)** (score: 3.4) — Proposes AI Network Security Agents for routers to provide intelligent, adaptive security capabiliti - **[draft-huang-rats-agentic-eat-cap-attest](https://datatracker.ietf.org/doc/draft-huang-rats-agentic-eat-cap-attest/)** (score: 3.4) — Extends Entity Attestation Token (EAT) to support capability attestation for agentic AI systems. Ena - **[draft-romanchuk-normative-admissibility](https://datatracker.ietf.org/doc/draft-romanchuk-normative-admissibility/)** (score: 3.4) — Establishes a framework for evaluating whether autonomous agent speech acts are admissible based on - **[draft-tan-ccamp-uonaco-problem-statement](https://datatracker.ietf.org/doc/draft-tan-ccamp-uonaco-problem-statement/)** (score: 3.4) — Defines requirements for unified orchestration between optical networks and AI computing to enable c - **[draft-jimenez-tbd-robotstxt-update](https://datatracker.ietf.org/doc/draft-jimenez-tbd-robotstxt-update/)** (score: 3.4) — Proposes updates to robots.txt standard to handle AI-specific crawlers with new syntax for user-agen - **[draft-thomson-aipref-sup](https://datatracker.ietf.org/doc/draft-thomson-aipref-sup/)** (score: 3.4) — Defines simple format for content usage preference expressions with HTTP header field. Updates RFC93 - **[draft-zhu-anima-service-intent](https://datatracker.ietf.org/doc/draft-zhu-anima-service-intent/)** (score: 3.4) — Defines a structured semantic model for expressing service-level objectives and constraints across n - **[draft-cosmos-protocol-specification](https://datatracker.ietf.org/doc/draft-cosmos-protocol-specification/)** (score: 3.3) — Defines comprehensive badge-based identity and communication system with trust scoring, post-quantum - **[draft-jeong-opsawg-intent-based-sdv-framework](https://datatracker.ietf.org/doc/draft-jeong-opsawg-intent-based-sdv-framework/)** (score: 3.3) — Proposes intent-based management framework for Software-Defined Vehicles in ITS environments. Covers - **[draft-diaconu-agents-authz-info-sharing](https://datatracker.ietf.org/doc/draft-diaconu-agents-authz-info-sharing/)** (score: 3.2) — Addresses authorization challenges in distributed multi-agent systems across multiple domains. Cover - **[draft-ahn-opsawg-5g-security-i2nsf-framework](https://datatracker.ietf.org/doc/draft-ahn-opsawg-5g-security-i2nsf-framework/)** (score: 3.2) — Proposes an integrated security framework for 5G edge networks using I2NSF architecture with Intent- - **[draft-zhao-detnet-enhanced-use-cases](https://datatracker.ietf.org/doc/draft-zhao-detnet-enhanced-use-cases/)** (score: 3.2) — Describes enhanced use cases for scaling deterministic networks beyond RFC8578, covering industrial