Visual Reasoning through Tool-supervised Reinforcement Learning

• URL: http://arxiv.org/abs/2604.19945v1
• Date: Tue, 21 Apr 2026 19:48:19 GMT
• Title: Visual Reasoning through Tool-supervised Reinforcement Learning
• Abstract summary: We propose a novel Tool-supervised Reinforcement Learning (ToolsRL) framework, with direct tool supervision for more effective tool-use learning.<n>We focus on a series of simple, native, and interpretable visual tools, including zoom-in, rotate, flip, and draw point/line.<n>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.
• Score: 18.76805336754779
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning [66.24374176797075]
  We introduce textbfAdaReasoner, a family of multimodal models that learn tool use as a general reasoning skill rather than as tool-specific or explicitly supervised behavior.<n>AdaReasoner is enabled by (i) a scalable data curation pipeline exposing models to long-horizon, multi-step tool interactions; (ii) Tool-GRPO, a reinforcement learning algorithm that prioritizes tool selection and sequencing based on end-task success; and (iii) an adaptive learning mechanism that dynamically regulates tool usage.
  arXiv  Detail & Related papers  (2026-01-26T16:04:43Z)
• Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction [31.689383152872534]
  ToolMaster is a framework that shifts tool use from imitating golden tool-calling trajectories to actively learning tool usage through interaction with the environment.<n>To optimize LLMs for tool planning and invocation, ToolMaster adopts a trial-and-execution paradigm.<n> Experimental results demonstrate that ToolMaster significantly outperforms existing baselines in terms of generalization and robustness across unseen or unfamiliar tools.
  arXiv  Detail & Related papers  (2026-01-19T06:46:33Z)
• Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning [63.071280297939005]
  We present Transductive Visual Programming (TVP), a novel framework that builds new tools from its own experience rather than speculation.<n>TVP achieves state-of-the-art performance, outperforming GPT-4o by 22% and the previous best visual programming system by 11%.<n>Our work establishes experience-driven transductive tool creation as a powerful paradigm for building self-evolving visual programming agents.
  arXiv  Detail & Related papers  (2025-12-24T04:30:21Z)
• VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection [47.259066449806866]
  VisTA is a new reinforcement learning framework that empowers visual agents to dynamically explore, select, and combine tools from a diverse library based on empirical performance.<n>We show that VisTA achieves substantial performance gains over training-free baselines.<n>These results highlight VisTA's ability to enhance generalization, adaptively utilize diverse tools, and pave the way for flexible, experience-driven visual reasoning systems.
  arXiv  Detail & Related papers  (2025-05-26T17:59:17Z)
• Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning [63.31585771716123]
  Large language models (LLMs) have shown remarkable reasoning capabilities via large-scale reinforcement learning (RL)<n>We introduce Tool-Star, an RL-based framework designed to empower LLMs to autonomously invoke multiple external tools during stepwise reasoning.<n>Tool-Star integrates six types of tools and incorporates systematic designs in both data synthesis and training.
  arXiv  Detail & Related papers  (2025-05-22T09:00:19Z)
• Towards Completeness-Oriented Tool Retrieval for Large Language Models [60.733557487886635]
  Real-world systems often incorporate a wide array of tools, making it impractical to input all tools into Large Language Models. Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions. We propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
  arXiv  Detail & Related papers  (2024-05-25T06:41:23Z)
• Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum [42.36892453363961]
  We propose a novel tool learning framework to train large language models (LLMs) to use complicated tools in real-world scenarios. We first propose a multi-stage learning method to teach the LLM to use various tools from an easy-to-difficult curriculum. We then propose the Iterative Self-instruct from Introspective Feedback to dynamically construct the dataset to improve the ability to use the complicated tool.
  arXiv  Detail & Related papers  (2023-08-27T07:53:00Z)
• Making Language Models Better Tool Learners with Execution Feedback [36.30542737293863]
  Tools serve as pivotal interfaces that enable humans to understand and reshape the environment. Existing tool learning methodologies induce large language models to utilize tools indiscriminately. We propose Tool leaRning wIth exeCution fEedback (TRICE), a two-stage end-to-end framework that enables the model to continually learn through feedback derived from tool execution.
  arXiv  Detail & Related papers  (2023-05-22T14:37:05Z)
• Tool Learning with Foundation Models [158.8640687353623]
  With the advent of foundation models, AI systems have the potential to be equally adept in tool use as humans. Despite its immense potential, there is still a lack of a comprehensive understanding of key challenges, opportunities, and future endeavors in this field.
  arXiv  Detail & Related papers  (2023-04-17T15:16:10Z)

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.