SOURCE-LINKED INTELLIGENCE

Agent-Editing World Model: Rethinking World Modeling for LLM Agents

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse environments. To further improve agent performance, existing language world models typically predict environment observations, yet reconstructing high-entropy, execution-dependent tool responses offers limited value when real feedback is available. Meanwhile, agents suffer from \emph{task-state contamination}, where unsupported assumptions and outdated plans persist in history and distort subsequent decisions. We propose the \textbf{Agent-Editing World Model (AEWM)}, which models how

Read original source ↗ Open in workspace

recordType

paper

region

Global