Metraipolis › archive › dc_7947f2e8def1
Bayesian Partner Modelling enables Adaptive Replanning for LLM Coordination — arXiv:2608.18490
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18490
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T13:43:15.849Z
- SHA-256 of the archived text
f3167024c6c5051abe2aee276ee48bd2ec1de227a349df85f66e7791ee3f1268- Stable URL of this page
https://metraipolis.com/documento/dc_7947f2e8def1
How to cite
Bayesian Partner Modelling enables Adaptive Replanning for LLM Coordination — arXiv:2608.18490 — arXiv (en), https://arxiv.org/abs/2608.18490 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7947f2e8def1 (Metraipolis archive dc_7947f2e8def1, sha256 f3167024c6c5051abe2aee276ee48bd2ec1de227a349df85f66e7791ee3f1268)
BibTeX
@misc{dc7947f2e8def1,
title = {Bayesian Partner Modelling enables Adaptive Replanning for LLM Coordination — arXiv:2608.18490},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18490},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7947f2e8def1; sha256 f3167024c6c5051abe2aee276ee48bd2ec1de227a349df85f66e7791ee3f1268},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18490. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent Large Language Model (LLM) systems often struggle to collaborate with new teammates whose strategies shift mid-task. Because agents execute multi-step or temporally extended skills, they frequently continue executing outdated plans long after public evidence shows that a partner has changed its skill. Existing methods either treat partner tracking as passive context-leaving the agent aware of the shift but slow to act-or replan indiscriminately. We introduce BayesBeliefAgent, which pairs a hierarchical LLM planner with a Bayesian tracking module. Rather than replanning constantly, our agent interrupts its current skill only when a partner's actions directly contradict the inferred skill. Beyond standard reward, we evaluate performance using replanning efficiency and the belief-action gap: the fraction of total decisions where an agent with a correct partner estimate executes a non-complementary skill. Across benchmark Overcooked environments, contradiction-conditioned control drastically narrows this belief-action gap while requiring an order of magnitude fewer replans than heuristic methods Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2608.18490 — 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 2026-10-18T13:40:43.011Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).