VLA-R1: Enhancing Reasoning in Vision-Language-Action Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Angen, Zhang, Zeyu, Wang, Boyuan, Wang, Xiaofeng, Zhang, Dapeng, Zhu, Zheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914071540924416
author Ye, Angen
Zhang, Zeyu
Wang, Boyuan
Wang, Xiaofeng
Zhang, Dapeng
Zhu, Zheng
author_facet Ye, Angen
Zhang, Zeyu
Wang, Boyuan
Wang, Xiaofeng
Zhang, Dapeng
Zhu, Zheng
contents Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack explicit step-by-step reasoning, instead emitting final actions without considering affordance constraints or geometric relations. Their post-training pipelines also rarely reinforce reasoning quality, relying primarily on supervised fine-tuning with weak reward design. To address these challenges, we present VLA-R1, a reasoning-enhanced VLA that integrates Reinforcement Learning from Verifiable Rewards (RLVR) with Group Relative Policy Optimization (GRPO) to systematically optimize both reasoning and execution. Specifically, we design an RLVR-based post-training strategy with verifiable rewards for region alignment, trajectory consistency, and output formatting, thereby strengthening reasoning robustness and execution accuracy. Moreover, we develop VLA-CoT-13K, a high-quality dataset that provides chain-of-thought supervision explicitly aligned with affordance and trajectory annotations. Furthermore, extensive evaluations on in-domain, out-of-domain, simulation, and real-robot platforms demonstrate that VLA-R1 achieves superior generalization and real-world performance compared to prior VLA methods. We plan to release the model, code, and dataset following the publication of this work. Code: https://github.com/GigaAI-research/VLA-R1. Website: https://gigaai-research.github.io/VLA-R1.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01623
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
Ye, Angen
Zhang, Zeyu
Wang, Boyuan
Wang, Xiaofeng
Zhang, Dapeng
Zhu, Zheng
Computer Vision and Pattern Recognition
Robotics
Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack explicit step-by-step reasoning, instead emitting final actions without considering affordance constraints or geometric relations. Their post-training pipelines also rarely reinforce reasoning quality, relying primarily on supervised fine-tuning with weak reward design. To address these challenges, we present VLA-R1, a reasoning-enhanced VLA that integrates Reinforcement Learning from Verifiable Rewards (RLVR) with Group Relative Policy Optimization (GRPO) to systematically optimize both reasoning and execution. Specifically, we design an RLVR-based post-training strategy with verifiable rewards for region alignment, trajectory consistency, and output formatting, thereby strengthening reasoning robustness and execution accuracy. Moreover, we develop VLA-CoT-13K, a high-quality dataset that provides chain-of-thought supervision explicitly aligned with affordance and trajectory annotations. Furthermore, extensive evaluations on in-domain, out-of-domain, simulation, and real-robot platforms demonstrate that VLA-R1 achieves superior generalization and real-world performance compared to prior VLA methods. We plan to release the model, code, and dataset following the publication of this work. Code: https://github.com/GigaAI-research/VLA-R1. Website: https://gigaai-research.github.io/VLA-R1.
title VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2510.01623