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.
@article{arxiv.2510.24645,
title = {FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use},
author = {Zengzhuang Xu and Bingguang Hao and Zechuan Wang and Yuntao Wen and Xinyi Xu and Yang Liu and Long Chen and Dong Wang and Maolin Wang and Tong Zhao and Yicheng Chen and Cunyin Peng and Jinjie Gu and Leilei Gan and Xiangyu Zhao and Chenyi Zhuang and Shi Gu},
journal= {arXiv preprint arXiv:2510.24645},
year = {2025}
}