docs: add Six Sigma Agent, AgileCoder, Reflexion citations to taxonomy paper
Incorporate findings from literature survey: Six Sigma Agent (arXiv:2601.22290) as the only prior explicit PM/OM-named framework, AgileCoder for Scrum sprints, Reflexion as implicit PDCA, CAMEL for role theory.
This commit is contained in:
@@ -141,6 +141,11 @@ sequential phases (design, coding, testing, documentation). Despite the
|
||||
``company'' framing, the execution model is a \emph{linear pipeline} with
|
||||
pair-programming-style chat between adjacent roles.
|
||||
|
||||
\textbf{AgileCoder} \citep{nguyen2024agilecoder} is the first framework to
|
||||
explicitly adopt sprint-based iteration, assigning Scrum Master and Product
|
||||
Manager roles to LLM agents with a Dynamic Code Graph Generator tracking
|
||||
inter-file dependencies between sprints.
|
||||
|
||||
\textbf{CrewAI} organizes agents into ``crews'' with a ``manager'' agent
|
||||
orchestrating task delegation---an implicit \emph{hierarchical management}
|
||||
model with single-point-of-failure coordination.
|
||||
@@ -150,6 +155,16 @@ framework where agents negotiate through multi-turn dialogue. The implicit
|
||||
model is \emph{committee decision-making}---all agents see all messages,
|
||||
consensus emerges through discussion.
|
||||
|
||||
\textbf{The Six Sigma Agent} \citep{patel2026sixsigma} decomposes tasks
|
||||
into atomic dependency trees, executes each node $n$ times with independent
|
||||
LLM samples, and uses consensus voting to achieve defect rates scaling as
|
||||
$O(p^{\lceil n/2 \rceil})$---reaching 3.4 DPMO (the Six Sigma threshold)
|
||||
at $n=13$.
|
||||
|
||||
\textbf{Reflexion} \citep{shinn2023reflexion} implements a de facto PDCA
|
||||
loop through verbal reinforcement: Plan $\to$ Act $\to$ Evaluate (Check)
|
||||
$\to$ Reflect (Act), though it does not name this structure explicitly.
|
||||
|
||||
\textbf{ArcheFlow} \citep{nennemann2026archeflow} explicitly applies PDCA
|
||||
quality cycles with Jungian archetypal roles, representing the first
|
||||
framework to deliberately adopt a named PM/OM methodology with formal
|
||||
@@ -158,11 +173,17 @@ convergence criteria.
|
||||
\subsection{The Gap}
|
||||
|
||||
Despite the variety of frameworks, the PM/OM methods actually employed
|
||||
cluster tightly around three approaches: (1) waterfall-style sequential
|
||||
phases, (2) role-based team simulation, and (3) informal ``manager''
|
||||
delegation. Methods from lean manufacturing, statistical process control,
|
||||
military decision-making, innovation management, and constraint theory
|
||||
remain entirely unexplored in the agent orchestration literature.
|
||||
cluster tightly around four approaches: (1) waterfall-style sequential
|
||||
phases (MetaGPT, ChatDev), (2) role-based team simulation (CAMEL
|
||||
\citep{li2023camel}, CrewAI), (3) informal ``manager'' delegation
|
||||
(AutoGen), and (4) agile sprints (AgileCoder). The Six Sigma Agent
|
||||
\citep{patel2026sixsigma} is a notable exception---the only framework to
|
||||
explicitly name a PM/OM method as its primary architectural contribution.
|
||||
|
||||
Methods from lean manufacturing, constraint theory, military
|
||||
decision-making, innovation management, and failure analysis remain
|
||||
unexplored in the peer-reviewed agent orchestration literature, despite
|
||||
strong structural compatibility with agent constraints.
|
||||
|
||||
% ============================================================
|
||||
\section{Taxonomy of PM/OM Methods}
|
||||
|
||||
Reference in New Issue
Block a user