{"ID":2849239,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.24645","arxiv_id":"2510.24645","title":"FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use","abstract":"Function calling (FC) empowers large language models (LLMs) and autonomous agents to interface with external tools, a critical capability for solving complex, real-world problems. As this ability becomes increasingly central to advanced AI systems, the need for high-quality, multi-turn training data to develop and refine it cannot be overstated. Existing data synthesis methods, such as random environment sampling or multi-agent role-playing, are not powerful enough to generate high-quality data in real-world environments. Practical challenges come in three folds: targeted data synthesis, hard query construction, and multi-turn logical dependency. To address these structural deficiencies, we present FunReason-MT, a novel data synthesis framework for real-world multi-turn tool use. FunReason-MT resolves the complexity barrier in multi-turn FC data by employing 1) Environment-API Graph Interactions to gather varied high-quality trajectories with targeted tool, 2) Advanced Tool-Query Synthesis to simplify hard query construction, and 3) Guided Iterative Chain for sophisticated CoT generation. Evaluations on Berkeley Function-Calling Leaderboard (BFCLv3) demonstrate the power of our framework: a 4B model built upon FunReason-MT generated data achieves state-of-the-art performance among comparable-sized models. Further performance improvements on BFCLv4 confirm that FunReason-MT provides a reliable and robust source for agentic learning.","short_abstract":"Function calling (FC) empowers large language models (LLMs) and autonomous agents to interface with external tools, a critical capability for solving complex, real-world problems. As this ability becomes increasingly central to advanced AI systems, the need for high-quality, multi-turn training data to develop and refi...","url_abs":"https://arxiv.org/abs/2510.24645","url_pdf":"https://arxiv.org/pdf/2510.24645v2","authors":"[\"Zengzhuang Xu\",\"Bingguang Hao\",\"Zechuan Wang\",\"Yuntao Wen\",\"Xinyi Xu\",\"Yang Liu\",\"Long Chen\",\"Dong Wang\",\"Maolin Wang\",\"Tong Zhao\",\"Yicheng Chen\",\"Cunyin Peng\",\"Jinjie Gu\",\"Leilei Gan\",\"Xiangyu Zhao\",\"Chenyi Zhuang\",\"Shi Gu\"]","published":"2025-10-28T17:15:26Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}