Metraipolis › archive › dc_476b9ecd86aa

MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games — arXiv:2609.06563

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.06563
License (as archived): CC0-1.0
Archived: 2026-10-16T13:58:58.309Z
SHA-256 of the archived text: 952c30045bb1b8b22b92dd388fc84d8555506e5f7d1b72ca3b3f8da53e5c07fe
Stable URL of this page: https://metraipolis.com/documento/dc_476b9ecd86aa

How to cite

MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games — arXiv:2609.06563 — arXiv (en), https://arxiv.org/abs/2609.06563 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_476b9ecd86aa (Metraipolis archive dc_476b9ecd86aa, sha256 952c30045bb1b8b22b92dd388fc84d8555506e5f7d1b72ca3b3f8da53e5c07fe)

BibTeX

@misc{dc476b9ecd86aa,
  title = {MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games — arXiv:2609.06563},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06563},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_476b9ecd86aa; sha256 952c30045bb1b8b22b92dd388fc84d8555506e5f7d1b72ca3b3f8da53e5c07fe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06563. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Social deduction games (SDGs) require agents to reason under partial observability by maintaining relational beliefs about hidden roles and team alignments. While recent LLM-agent approaches improve gameplay through prompting and preference optimization, they often optimize actions and in-game speech without explicitly grounding them in such beliefs. This frequently leads to strategically inconsistent behavior, especially for compact LLM agents. We introduce Multi-Agent Relational Belief Optimization (MARBO), a belief-grounded preference optimization framework that leverages relational beliefs to guide strategic decisions and in-game speech. MARBO provides preference feedback only when behaviors are supported by reliable relational beliefs and lead to strategically favorable social outcomes, encouraging more consistent learning under uncertainty. Experiments on representative SDGs show that MARBO enables compact LLM agents to consistently outperform existing baselines. The Code is available on this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.06563 — 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 2026-10-16T13:39:43.178Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).