arXiv cs.AI· Xin Heng·· 2 天前AI 评分47
多智能体协作的全局一致性：当每个 Agent 都对、团队却错了
Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration
AI 导读
论文提出"全局一致性"问题：AI 智能体各自做出局部有效决策，联合结果却无效，根源是共享状态缺失而非智能不足。其 Observation-Aliasing Impossibility Theorem 给出精确边界——若 k 个不可区分世界需要两两不相交的动作，随机化最坏情况成功率上限为 1/k，更多推理、角色、消息或采样都无法弥补。
正文 · 原文
Abstract: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 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. The smallest sufficient context is NP-hard to find, yet counterexample-guided refinement finds a sufficient one and recertifies it as rules change. We give local-to-global runtime semantics X = (H, C, G, F; D): topology H records overlapping scopes; category C governs state-changing actions; groupoid G keeps reversible translations; sheaf F tests whether local views glue into one world; and history D keeps only what alters legal futures. Each preserves the needed information as state is split, translated, or changed. Models propose; the harness owns shared state and governs commit. Ten studies test the boundary. On a revision benchmark, a frontier model scores 40/40 when the deciding event is visible; hidden, every arm is consistent with chance (1/3); one restored fact returns 40/40. On TeamBench, ordinary teams exceed a shared budget in 5/5 runs, a visible live count leaves 4/5, and commit enforcement leaves 0/5. In tau2-bench Telecom, current-state checks score 0.07 after silent reverts; the harness scores 1.00. Refinement keeps a sufficient context through rule changes at 28% of the all-field cost. Solvers that already own the state tie it, as predicted. Local intelligence cannot substitute for missing global state.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.02036 [cs.AI] |
| (or arXiv:2610.02036v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02036 arXiv-issued DOI via DataCite |
Submission history
From: Xin Heng [view email]
[v1]
Thu, 1 Oct 2026 16:49:40 UTC (96 KB)
[v2]
Thu, 15 Oct 2026 01:36:37 UTC (69 KB)
来源：arXiv cs.AI · arxiv.org