Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration· 全局一致性：每个智能体都正确而团队仍出错
AI agents can each make locally valid decisions yet jointly produce an invalid result. We call this the global coherence problem: a failure of shared state, not merely of model intelligence. Our Observation-Aliasing Impossibility Theorem gives the exact boundary. A policy can guarantee a valid action exactly when all worlds producing the same observation share an admissible action. If k indistinguishable worlds require pairwise-disjoint actions, the best randomized worst-case success is 1/k; more reasoning, roles, messages, or samples cannot recover the missing distinction. A stronger model can reason better within its context, but it cannot see beyond it. We then give local-to-global runtime semantics X = (H, C, G, F; D): topology H records overlapping scopes; category C governs state-cha
探讨多智能体协作中的全局一致性问题及其解决方案
- 核心方法
- 提出了Observation-Aliasing Impossibility Theorem，定义了在多智能体系统中保证有效动作的精确边界，并提出了一个从局部到全局的运行时语义模型X = (H, C, G, F; D)。
- 适合谁读
- 研究者
- 要解决的问题
- 论文探讨了当多个AI智能体分别做出局部有效的决策时，整个团队却可能产生全局无效的结果，即全局一致性问题。
- 关键实验
- 未提供
- 主要贡献
- 1. 定义了多智能体系统中全局一致性问题的边界条件；2. 提出了一个模型来描述和解决这一问题。
- 意义与局限
- 该研究为多智能体系统的设计提供了重要的理论基础，指出单纯增加智能体的复杂性或通信量无法根本解决全局一致性问题。这一发现对于理解和设计更复杂的多智能体系统具有重要意义。