Planning with Reasoning using Vision Language World Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Delong, Moutakanni, Theo, Chung, Willy, Bang, Yejin, Ji, Ziwei, Bolourchi, Allen, Fung, Pascale
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914025433989120
author Chen, Delong
Moutakanni, Theo
Chung, Willy
Bang, Yejin
Ji, Ziwei
Bolourchi, Allen
Fung, Pascale
author_facet Chen, Delong
Moutakanni, Theo
Chung, Willy
Bang, Yejin
Ji, Ziwei
Bolourchi, Allen
Fung, Pascale
contents Effective planning requires strong world models, but high-level world models that can understand and reason about actions with semantic and temporal abstraction remain largely underdeveloped. We introduce the Vision Language World Model (VLWM), a foundation model trained for language-based world modeling on natural videos. Given visual observations, the VLWM first infers the overall goal achievements then predicts a trajectory composed of interleaved actions and world state changes. Those targets are extracted by iterative LLM Self-Refine conditioned on compressed future observations represented by Tree of Captions. The VLWM learns both an action policy and a dynamics model, which respectively facilitates reactive system-1 plan decoding and reflective system-2 planning via cost minimization. The cost evaluates the semantic distance between the hypothetical future states given by VLWM roll-outs and the expected goal state, and is measured by a critic model that we trained in a self-supervised manner. The VLWM achieves state-of-the-art Visual Planning for Assistance (VPA) performance on both benchmark evaluations and our proposed PlannerArena human evaluations, where system-2 improves the Elo score by +27% upon system-1. The VLWM models also outperforms strong VLM baselines on RoboVQA and WorldPrediction benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2509_02722
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Planning with Reasoning using Vision Language World Model
Chen, Delong
Moutakanni, Theo
Chung, Willy
Bang, Yejin
Ji, Ziwei
Bolourchi, Allen
Fung, Pascale
Artificial Intelligence
Effective planning requires strong world models, but high-level world models that can understand and reason about actions with semantic and temporal abstraction remain largely underdeveloped. We introduce the Vision Language World Model (VLWM), a foundation model trained for language-based world modeling on natural videos. Given visual observations, the VLWM first infers the overall goal achievements then predicts a trajectory composed of interleaved actions and world state changes. Those targets are extracted by iterative LLM Self-Refine conditioned on compressed future observations represented by Tree of Captions. The VLWM learns both an action policy and a dynamics model, which respectively facilitates reactive system-1 plan decoding and reflective system-2 planning via cost minimization. The cost evaluates the semantic distance between the hypothetical future states given by VLWM roll-outs and the expected goal state, and is measured by a critic model that we trained in a self-supervised manner. The VLWM achieves state-of-the-art Visual Planning for Assistance (VPA) performance on both benchmark evaluations and our proposed PlannerArena human evaluations, where system-2 improves the Elo score by +27% upon system-1. The VLWM models also outperforms strong VLM baselines on RoboVQA and WorldPrediction benchmark.
title Planning with Reasoning using Vision Language World Model
topic Artificial Intelligence
url https://arxiv.org/abs/2509.02722