← Back to all news
arXiv Computation and Language By Guangfeng Cai, Kaibing Yang, Shuo He, Yu Li, Shengtian Yang, Jiaqi Lv, Lei Feng

Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making

Read the original on arXiv Computation and Language →

The paper introduces Agent-Authored World Modeling (AAWM), a training method that replaces traditional next-observation prediction with decision-oriented supervision. AAWM constructs training targets by having the agent identify what it needs to know before acting, then retrieves relevant transition evidence across trajectories to synthesize these needs into learning signals. Experiments across multiple environments demonstrate that this decision-aware approach yields more effective learning than conventional next-observation prediction.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Oct 23

Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model

The paper introduces the Pitfall Anticipation World Model (PAWM), a selective guidance system for black-box large language model agents. PAWM predicts imminent failures in a bounded multi-step future and intervenes only when a potential pitfall is detected, reducing costly and often uninformative step-by-step predictions. Trained first with supervised fine-tuning on synthetic pitfall-labeled data and then co-trained with a black-box LLM, PAWM boosts Claude Sonnet 4.5’s performance by 24.3% on ScienceWorld and 7.7% on WebArena-Lite, outperforming several baselines.

By Jiongxiao Wang, Han Ding, Youzhi Luo, Yawei Wang, Yun Zhou, Linbo Liu, Panpan Xu
llmsagentsfine-tuning
More like this →