Metraipolis › archive › dc_e45b9c55df45
Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration — arXiv:2610.02036
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.02036
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:06:50.039Z
- SHA-256 of the archived text
0b99ac38c028bafbe6e6b9178156fb70fc35974efbaabd0815c75daf925d6d41- Stable URL of this page
https://metraipolis.com/documento/dc_e45b9c55df45
How to cite
Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration — arXiv:2610.02036 — arXiv (en), https://arxiv.org/abs/2610.02036 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e45b9c55df45 (Metraipolis archive dc_e45b9c55df45, sha256 0b99ac38c028bafbe6e6b9178156fb70fc35974efbaabd0815c75daf925d6d41)
BibTeX
@misc{dce45b9c55df45,
title = {Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration — arXiv:2610.02036},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.02036},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e45b9c55df45; sha256 0b99ac38c028bafbe6e6b9178156fb70fc35974efbaabd0815c75daf925d6d41},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02036. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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-changing actions; groupoid G retains reversible translations; sheaf F tests whether local views glue into one world; and minimal history D keeps only distinctions that alter legal futures. Models propose; the harness owns shared state and governs commit. Nine studies test both the failure and its boundary. On a controlled revision benchmark, the same frontier model scores 40/40 when the deciding event is visible; when it is hidden, tested arms score 12--17/40, consistent with chance (1/3); restoring one authoritative fact returns 40/40. On TeamBench, ordinary teams exceed a shared budget in 5/5 runs, a visible live count leaves 4/5 violations, and commit enforcement leaves 0/5. In tau2-bench Telecom, current-state checks score 0.07 after silent reverts, while the harness scores 1.00. Where a conventional solver already owns the complete relevant state, it ties the harness as predicted. The counterintuitive conclusion is that local intelligence cannot substitute for missing global state. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.02036 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T10:21:27.994Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).