Metraipolis › archive › dc_e6efab6a2d4e
Towards a Belief-Based World Model for LLM Agents — arXiv:2609.00455
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00455
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:31:52.835Z
- SHA-256 of the archived text
165f1afd846f6c3955e2981fb98f50483bbed3823eee90356aff97f7fb45c362- Stable URL of this page
https://metraipolis.com/documento/dc_e6efab6a2d4e
How to cite
Towards a Belief-Based World Model for LLM Agents — arXiv:2609.00455 — arXiv (en), https://arxiv.org/abs/2609.00455 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6efab6a2d4e (Metraipolis archive dc_e6efab6a2d4e, sha256 165f1afd846f6c3955e2981fb98f50483bbed3823eee90356aff97f7fb45c362)
BibTeX
@misc{dce6efab6a2d4e,
title = {Towards a Belief-Based World Model for LLM Agents — arXiv:2609.00455},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00455},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6efab6a2d4e; sha256 165f1afd846f6c3955e2981fb98f50483bbed3823eee90356aff97f7fb45c362},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00455. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are being used as policies for autonomous decision-making and planning in many domains. Despite their strong reasoning capabilities, LLMs struggle with long-horizon tasks, especially under partial observability. World models are a promising way to enhance policy performance, both during training and inference. During inference, agents currently use world models to simulate the consequences of candidate actions before choosing an action, which can improve decision-making. However, we argue that simulation alone is an incomplete interface for decision-making under partial observability: simulation does not adequately capture uncertainty about the current state, which agents may need for accurate decision-making. We address this limitation with Belief-Based World Models (BB-WMs), which maintain a belief that LLMs can query to access information on what is known and uncertain about the current state. Before developing methods to learn accurate BB-WMs, this paper focuses on a more fundamental question: does exposing a world model's belief directly to an LLM policy improve decision-making? Our results show that giving LLM agents access to beliefs improves task performance under partial observability, while remaining complementary to existing simulation-based world models. Code: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.00455 — 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 2026-10-17T06:15:12.605Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).