{"ID":2889224,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.21836","arxiv_id":"2507.21836","title":"AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning","abstract":"Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools, but existing methods often rely on rigid, predefined tool-use patterns that risk degrading core language competence. Inspired by the human ability to adaptively select tools, we introduce AutoTIR, a reinforcement learning framework that enables LLMs to autonomously decide whether and which tool to invoke during the reasoning process, rather than following static tool-use strategies. AutoTIR leverages a hybrid reward mechanism that jointly optimizes for task-specific answer correctness, structured output adherence, and penalization of incorrect tool usage, thereby encouraging both precise reasoning and efficient tool integration. Extensive evaluations across diverse knowledge-intensive, mathematical, and general language modeling tasks demonstrate that AutoTIR achieves superior overall performance, significantly outperforming baselines and exhibits superior generalization in tool-use behavior. These results highlight the promise of reinforcement learning in building truly generalizable and scalable TIR capabilities in LLMs. The code and data are available at https://github.com/weiyifan1023/AutoTIR.","short_abstract":"Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools, but existing methods often rely on rigid, predefined tool-use patterns that risk d...","url_abs":"https://arxiv.org/abs/2507.21836","url_pdf":"https://arxiv.org/pdf/2507.21836v1","authors":"[\"Yifan Wei\",\"Xiaoyan Yu\",\"Yixuan Weng\",\"Tengfei Pan\",\"Angsheng Li\",\"Li Du\"]","published":"2025-07-29T14:12:28Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":611627,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2889224,"paper_url":"https://arxiv.org/abs/2507.21836","paper_title":"AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning","repo_url":"https://github.com/weiyifan1023/AutoTIR","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}