Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

The paper introduces a game-theoretic framework for coordinating multi-agent large language model (LLM) systems, modeling orchestrator–worker interactions as a bilevel coordination game. It analyzes textual reflection as stochastic movement over semantic memory states, providing finite-time bounds, lower bounds, and an information-theoretic impossibility result. Building on these insights, the authors propose Stochastic Reflective Memory Ascent (SRMA), a grounded evaluation mechanism that guarantees convergence under certain conditions and demonstrates improved performance on 500 SWE‑bench instances.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents