Beyond Prediction: Steering VLM Agents with Retrospective World Modeling

Excerpt

arXiv:2609.39101v1 Announce Type: cross Abstract: Equipping VLM agents with world modeling capabilities has shown strong potential for complex reasoning and long-horizon planning, while reducing the dependence of policy learning on costly real-world interactions. Existing methods mainly rely on prospective simulation to predict the consequences of candidate actions. However, this forward-only paradigm focuses on what will happen next and provides limited constraints for verifying whether an acti