World Modeling Makes a Better Planner: Dual Preference Optimization for
  Embodied Task Planning

Siyin Wang; Zhaoye Fei; Qinyuan Cheng; Shiduo Zhang; Panpan Cai; Jinlan Fu; Xipeng Qiu

返回文献探索

Paper · arXiv 2503.10480

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning

Siyin Wang, Zhaoye Fei, Qinyuan Cheng, Shiduo Zhang, Panpan Cai, Jinlan Fu, Xipeng Qiu

57 upvotesMarch 13, 2025arXiv 预印本

AI 摘要

Dual Preference Optimization (D$^2$PO) enhances embodied task planning in large vision-language models by jointly optimizing state prediction and action selection using preference learning and tree search for efficient trajectory collection.

large vision-language modelsembodied task planningdependency constraintsefficiencyworld modelspreference learningDual Preference OptimizationD$^2$POstate predictionaction selectiontree searchVoTa-BenchQwen2-VLLLaVA-1.6LLaMA-3.2task success ratesexecution paths

Abstract

Recent advances in large vision-language models (LVLMs) have shown promise for embodied task planning, yet they struggle with fundamental challenges like dependency constraints and efficiency. Existing approaches either solely optimize action selection or leverage world models during inference, overlooking the benefits of learning to model the world as a way to enhance planning capabilities. We propose Dual Preference Optimization (D^2PO), a new learning framework that jointly optimizes state prediction and action selection through preference learning, enabling LVLMs to understand environment dynamics for better planning. To automatically collect trajectories and stepwise preference data without human annotation, we introduce a tree search mechanism for extensive exploration via trial-and-error. Extensive experiments on VoTa-Bench demonstrate that our D^2PO-based method significantly outperforms existing methods and GPT-4o when applied to Qwen2-VL (7B), LLaVA-1.6 (7B), and LLaMA-3.2 (11B), achieving superior task success rates with more efficient execution paths.