paper-with-me

홈 › Papers

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents

2026-05-18 · Xiongbin Wu, Zhihao Luo, Shanzhe Lei, Lechao Zhang, Xuhong Wang, Jie Yang, Zhonglong Zheng, Yuanjie Zheng, Xin Tan, Wei Liu arxiv

Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple turns of visual perception and action execution. However, existing methods still rely primarily on Supervised Fine-Tuning (SFT) with expert demonstrations, while the advanced reinforcement learning (RL) algorithm, specifically Group Relative Policy Optimization (GRPO), has not been effectively employed for multi-turn RL in these tasks because standard GRPO requires full trajectories as training samples which leads to excessively long context and noise. To address this issue, we propose GROW, a RL framework for open-world VLM agents that decomposes collected trajectories into state-action samples, and computes advantages between these samples rather than treating a full trajectory as a single entity. We further provide a surrogate analysis indicating that, even though the grouped samples are conditioned on different local states rather than an identical prompt context, the objective can preserve the core relative policy optimization signal of GRPO under simplifying assumptions. Experiments on more than 800 Minecraft tasks show that our method achieves state-of-the-art (SOTA) performance, demonstrating the effectiveness of our proposed RL framework for open-world VLM agents.

📄 PDF Abstract BibTeX arXiv:2605.20246

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Advances in GRPO for Generation Models: A Survey

2026-02-21 · Zexiang Liu, Xianglong He, Yangguang Li arxiv

Large-scale flow matching models have achieved strong performance across generative tasks such as text-to-image, video, 3D, and speech synthesis. However, aligning their outputs with human preferences and task-specific o…

Reinforcement LearningSpeech SynthesisVideo GenerationImage Editing

Temporal GRPO: Beyond Trajectory-Level Credit in Vision-Language-Action Reinforcement Learning

2026-08-13 · Yao Zhou, Hang Gao, Fengge Wu, Changwen Zheng 외 arxiv

Outcome-driven reinforcement learning offers a scalable way to post-train vision-language-action (VLA) policies from sparse task-success feedback. In common GRPO-based VLA post-training, one rollout-level advantage is ap…

Reinforcement Learning

RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs

2025-05-19 · Soumya Rani Samineni, Durgesh Kalwar, Karthik Valmeekam, Kaya Stechly 외

Reinforcement learning-based post-training of large language models (LLMs) has recently gained attention, particularly following the release of DeepSeek R1, which applied GRPO for fine-tuning. Amid the growing hype aroun…

GSM8K

A First-Order Logic-Based Alternative to Reward Models in RLHF

2025-12-16 · Chunjin Jian, Xinhua Zhu arxiv

Reinforcement Learning from Human Feedback (RLHF) plays a crucial role in aligning large language models (LLMs) with human values and preferences. However, the quality and stability of the trained reward model largely de…

Reinforcement Learning

TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization

2025-06-10 · Zengjue Chen, Runliang Niu, He Kong, Qi Wang

Recent advances in Vision-Language-Action (VLA) model have demonstrated strong generalization capabilities across diverse scenes, tasks, and robotic platforms when pretrained at large-scale datasets. However, these model…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Vision-Language-Action