VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning

• URL: http://arxiv.org/abs/2603.14523v1
• Date: Sun, 15 Mar 2026 17:59:51 GMT
• Title: VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
• Abstract summary: Vision-Language-Action (VLA) models have shown promising capabilities for embodied intelligence.<n>We propose VLA-Thinker, a thinking-with-image reasoning framework that models perception as a dynamically invocable reasoning action.
• Score: 40.136343449141265
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models have shown promising capabilities for embodied intelligence, but most existing approaches rely on text-based chain-of-thought reasoning where visual inputs are treated as static context. This limits the ability of the model to actively revisit the environment and resolve ambiguities during long-horizon tasks. We propose VLA-Thinker, a thinking-with-image reasoning framework that models perception as a dynamically invocable reasoning action. To train such a system, we introduce a two-stage training pipeline consisting of (1) an SFT cold-start phase with curated visual Chain-of-Thought data to activate structured reasoning and tool-use behaviors, and (2) GRPO-based reinforcement learning to align complete reasoning-action trajectories with task-level success. Extensive experiments on LIBERO and RoboTwin 2.0 benchmarks demonstrate that VLA-Thinker significantly improves manipulation performance, achieving 97.5% success rate on LIBERO and strong gains across long-horizon robotic tasks. Project and Codes: https://cywang735.github.io/VLA-Thinker/ .

Related papers

• ViThinker: Active Vision-Language Reasoning via Dynamic Perceptual Querying [15.728211622542267]
  ViThinker is a framework that enables vision-language models to autonomously generate decision tokens triggering the synthesis of expert-aligned visual features on demand.<n>ViThinker internalizes vision-expert capabilities during training, performing generative mental simulation during inference without external tool calls.
  arXiv  Detail & Related papers  (2026-02-02T22:29:57Z)
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models [57.75717492488268]
  Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models.<n>Supervised Finetuning (SFT) requires hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training.<n>We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations.
  arXiv  Detail & Related papers  (2025-12-16T18:26:38Z)
• Guiding the Inner Eye: A Framework for Hierarchical and Flexible Visual Grounded Reasoning [6.800544911407401]
  GRiP (Guided Reasoning and Perception) is a novel training framework for visual grounded reasoning.<n> GRiP cultivates robust and flexible visual grounded reasoning by explicitly guiding the model's perceptual focus and logical pathways.<n> GRiP achieves state-of-the-art results among open-source models on the highly challenging TreeBench and V* Bench.
  arXiv  Detail & Related papers  (2025-11-27T07:18:25Z)
• ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model [61.29164681694533]
  ViPER is a self-bootstrapping framework specifically designed to enable iterative evolution through self-critiquing and self-prediction.<n>Qwen-Viper consistently demonstrates superior performance across different vision-language scenarios while maintaining generalizability.
  arXiv  Detail & Related papers  (2025-10-28T10:42:57Z)
• Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models [63.69856480318313]
  AGILE formulates jigsaw solving as an interactive process, enabling the model to progressively engage with the environment.<n>We show that AGILE substantially boosts performance on jigsaw tasks of varying complexity.<n>We also demonstrate strong generalization across 9 general vision tasks, achieving an average improvement of 3.1%.
  arXiv  Detail & Related papers  (2025-10-01T17:58:05Z)
• More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models [17.431298099935344]
  Reasoning has emerged as a pivotal capability in Large Language Models (LLMs)<n>Recent research has sought to extend reasoning to Vision-Language Models (VLMs)<n>Our study uncovers the dual nature of multimodal reasoning, leading to recognition failures on otherwise basic visual questions.<n>We propose Vision-Anchored Policy Optimization (VAPO), a simple yet effective method that explicitly steers the reasoning process toward visually grounded trajectories.
  arXiv  Detail & Related papers  (2025-09-30T06:37:47Z)
• dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought [66.78110237549087]
  Vision-Language-Action (VLA) models are emerging as a next-generation paradigm for robotics.<n>We introduce dVLA, a diffusion-based VLA that unifies visual perception, language reasoning, and robotic control in a single system.
  arXiv  Detail & Related papers  (2025-09-30T02:36:11Z)
• CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models [89.44024245194315]
  We introduce a method that incorporates explicit visual chain-of-thought (CoT) reasoning into vision-language-action models (VLAs)<n>We introduce CoT-VLA, a state-of-the-art 7B VLA that can understand and generate visual and action tokens.<n>Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks.
  arXiv  Detail & Related papers  (2025-03-27T22:23:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.