Metraipolis › archive › dc_541a4be80d4e

EpiAgent: Epistemic Self-Play for LLM Agents — arXiv:2610.40227

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40227
License (as archived)
CC0-1.0
Archived
2026-10-31T06:06:50.939Z
SHA-256 of the archived text
b917be0d0bff5d3806364ebb44a3912e95cfcfa9ae1fbd584edf420076f832ce
Stable URL of this page
https://metraipolis.com/documento/dc_541a4be80d4e

How to cite

EpiAgent: Epistemic Self-Play for LLM Agents — arXiv:2610.40227 — arXiv (en), https://arxiv.org/abs/2610.40227 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_541a4be80d4e (Metraipolis archive dc_541a4be80d4e, sha256 b917be0d0bff5d3806364ebb44a3912e95cfcfa9ae1fbd584edf420076f832ce)
BibTeX
@misc{dc541a4be80d4e,
  title = {EpiAgent: Epistemic Self-Play for LLM Agents — arXiv:2610.40227},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40227},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_541a4be80d4e; sha256 b917be0d0bff5d3806364ebb44a3912e95cfcfa9ae1fbd584edf420076f832ce},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40227. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Epistemic game theory explains an agent's strategic behavior via the beliefs it holds about others and how these beliefs are updated as the interactions unfold. Modern LLM-based agents, however, often lack an explicit mechanism for learning and updating such beliefs to guide decisions under incomplete information. To bridge this gap, we propose EpiAgent, a framework that equips LLM-based agents with an explicit, learnable epistemic layer, which maintains beliefs over others' private information and combines these beliefs with the agent's available information into an epistemic state for action selection. Concretely, the agent's policy is decomposed into two coupled stages: Epistemic Update, which updates these beliefs from interaction histories, and Action Planning, which selects actions conditioned on the updated epistemic state. By formulating their dependency as a bi-level optimization problem, we introduce Epistemic Self-Play, an algorithm that alternately optimizes the two stages through self-play, utilizing an intrinsic prediction reward to evaluate how well inferred beliefs predict subsequent observations. Empirical results across both mixed and competitive scenarios show that EpiAgent consistently outperforms prompting-based and RL-based baselines. Further analyses reveal the benefits of dedicated epistemic training, improvements in belief inference accuracy, and the contribution of learned beliefs to action planning. These results demonstrate the value of an explicit, learnable epistemic layer for effective multi-agent interactions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.40227 — 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 2026-10-31T06:06:38.434Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).