AAWM：让 LLM 智能体按自身决策需求构建世界模型，替代下一观测预测

View PDF HTML (experimental)

Abstract:Recent studies on world modeling for Large Language Model (LLM) agents typically formulate the learning objective as next-observation prediction. However, this objective ties supervision to what a transition happens to reveal, which may omit the dynamics most relevant to the agent's current decision. To bridge this gap, we propose Agent-Authored World Modeling (AAWM), a training procedure that constructs supervision from the policy's own decision needs. Specifically, at each state, the agent identifies what it needs to understand about the environment before acting. These needs drive the retrieval of relevant transition evidence across trajectories, which is then synthesized into training targets that capture decision-oriented dynamics instead of reconstructing the next observation. This aligns the training objective with the dynamics the policy needs before acting, not with the contents of the next observation. Experimental results validate the effectiveness of AAWM across multiple environments and training settings. These results show that decision-aware world-model targets provide a more effective learning signal than next-observation prediction.

Submission history

From: Guangfeng Cai [view email]
[v1] Wed, 24 Jun 2026 05:31:00 UTC (678 KB)
[v2] Sun, 1 Nov 2026 17:46:18 UTC (684 KB)