paper-with-me

Papers

OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning

2025-05-13 · Zhaochen Su, Linjie Li, Mingyang Song, Yunzhuo Hao, Zhengyuan Yang, Jun Zhang, Guanjie Chen, Jiawei Gu, Juntao Li, Xiaoye Qu, Yu Cheng

While humans can flexibly leverage interactive visual cognition for complex problem-solving, enabling Large Vision-Language Models (LVLMs) to learn similarly adaptive behaviors with visual tools remains challenging. A significant hurdle is the current lack of standardized infrastructure, which hinders integrating diverse tools, generating rich interaction data, and training robust agents effectively. To address these gaps, we introduce OpenThinkIMG, the first open-source, comprehensive end-to-end framework for tool-augmented LVLMs. It features standardized vision tool interfaces, scalable trajectory generation for policy initialization, and a flexible training environment. Furthermore, considering supervised fine-tuning (SFT) on static demonstrations offers limited policy generalization for dynamic tool invocation, we propose a novel reinforcement learning (RL) framework V-ToolRL to train LVLMs to learn adaptive policies for invoking external vision tools. V-ToolRL enables LVLMs to autonomously discover optimal tool-usage strategies by directly optimizing for task success using feedback from tool interactions. We empirically validate V-ToolRL on challenging chart reasoning tasks. Our RL-trained agent, built upon a Qwen2-VL-2B, significantly outperforms its SFT-initialized counterpart (+28.83 points) and surpasses established supervised tool-learning baselines like Taco and CogCom by an average of +12.7 points. Notably, it also surpasses prominent closed-source models like GPT-4.1 by +8.68 accuracy points. We hope OpenThinkIMG can serve as a foundational framework for advancing dynamic, tool-augmented visual reasoning, helping the community develop AI agents that can genuinely "think with images".

📄 PDF Abstract BibTeX arXiv:2505.08617

Code (1)

zhaochen0110/openthinkimg 공식 구현 pytorch

Tasks

Reinforcement Learning (RL)Visual Reasoning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use

2025-05-25 · Mingyuan Wu, Jingcheng Yang, Jize Jiang, Meitang Li 외

Reinforcement Learning Finetuning (RFT) has significantly advanced the reasoning capabilities of large language models (LLMs) by enabling long chains of thought, self-correction, and effective tool use. While recent work…

Multimodal ReasoningQuestion AnsweringVisual Question AnsweringVisual Reasoning

DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

2025-05-20 · Ziwei Zheng, Michael Yang, Jack Hong, Chenxiao Zhao 외

Large Vision-Language Models (VLMs) have shown strong capabilities in multimodal understanding and reasoning, yet they are primarily constrained by text-based reasoning processes. However, achieving seamless integration …

HallucinationMathematical ReasoningMultimodal Reasoningreinforcement-learning+2

MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning

2026-01-12 · Meng Lu, Yuxing Lu, Yuchen Zhuang, Megan Mullins 외 arxiv

Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning through iterative visual interaction. Med…

Reinforcement LearningMultimodal ReasoningVisual Reasoning

Visual Agentic Reinforcement Fine-Tuning

2025-05-20 · Ziyu Liu, Yuhang Zang, Yushan Zou, Zijian Liang 외

A key trend in Large Reasoning Models (e.g., OpenAI's o3) is the native agentic ability to use external tools such as web browsers for searching and writing/executing code for image manipulation to think with images. In …

Image Manipulation

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning

2025-10-14 · Xingang Guo, Utkarsh Tyagi, Advait Gosai, Paula Vergara 외 arxiv

Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to …