paper-with-me

Papers

Visual Reasoning through Tool-supervised Reinforcement Learning

2026-04-21 · Qihua Dong, Gozde Sahin, Pei Wang, Zhaowei Cai, Robik Shrestha, Hao Yang, Davide Modolo arxiv

In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Models. To achieve that, we propose a novel Tool-supervised Reinforcement Learning (ToolsRL) framework, with direct tool supervision for more effective tool-use learning. We focus on a series of simple, native, and interpretable visual tools, including zoom-in, rotate, flip, and draw point/line, whose tool supervision is easy to collect. A reinforcement learning curriculum is developed, where the first stage is solely optimized by a set of well motivated tool-specific rewards, and the second stage is trained with the accuracy targeted rewards while allowing calling tools. In this way, tool calling capability is mastered before using tools to complete visual reasoning tasks, avoiding the potential optimization conflict among those heterogeneous tasks. Our experiments have shown that the tool-supervised curriculum training is efficient and ToolsRL can achieve strong tool-use capabilities for complex visual reasoning tasks.

📄 PDF Abstract BibTeX arXiv:2604.19945

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningVisual Reasoning

Similar Papers 제목 키워드 기반

Reinforced Visual Perception with Tools

2025-09-01 · Zetong Zhou, Dongping Chen, Zixian Ma, Zhihan Hu 외 arxiv

Visual reasoning, a cornerstone of human intelligence, encompasses complex perceptual and logical processes essential for solving diverse visual problems. While advances in computer vision have produced powerful models f…

Reinforcement LearningVisual Reasoning

Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensing

2026-07-28 · Fengxiang Wang, Jiangnan Huang, Mingshuo Chen, Yueying Li 외 arxiv

Ultra-high-resolution (UHR) remote-sensing (RS) imagery provides fine-grained Earth-observation evidence over city-scale scenes, but poses a fundamental challenge for multimodal large language models (MLLMs): task-releva…

Reinforcement LearningVisual Reasoning

Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs

2025-11-24 · Meng Lu, Ran Xu, Yi Fang, Wenxuan Zhang 외 arxiv

While recent vision-language models (VLMs) demonstrate strong image understanding, their ability to "think with images", i.e., to reason through multi-step visual interactions, remains limited. We introduce VISTA-Gym, a …

Reinforcement LearningMultimodal ReasoningVisual Reasoning

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

VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection

2025-05-26 · Zeyi Huang, Yuyang Ji, Anirudh Sundara Rajan, Zefan Cai 외

We introduce VisTA, a new reinforcement learning framework that empowers visual agents to dynamically explore, select, and combine tools from a diverse library based on empirical performance. Existing methods for tool-au…

Diversityreinforcement-learningReinforcement LearningVisual Reasoning