FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917082915930112 |
|---|---|
| author | Xu, Zengzhuang Hao, Bingguang Wang, Zechuan Wen, Yuntao Xu, Xinyi Liu, Yang Chen, Long Wang, Dong Wang, Maolin Zhao, Tong Chen, Yicheng Peng, Cunyin Gu, Jinjie Gan, Leilei Zhao, Xiangyu Zhuang, Chenyi Gu, Shi |
| author_facet | Xu, Zengzhuang Hao, Bingguang Wang, Zechuan Wen, Yuntao Xu, Xinyi Liu, Yang Chen, Long Wang, Dong Wang, Maolin Zhao, Tong Chen, Yicheng Peng, Cunyin Gu, Jinjie Gan, Leilei Zhao, Xiangyu Zhuang, Chenyi Gu, Shi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24645 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use Xu, Zengzhuang Hao, Bingguang Wang, Zechuan Wen, Yuntao Xu, Xinyi Liu, Yang Chen, Long Wang, Dong Wang, Maolin Zhao, Tong Chen, Yicheng Peng, Cunyin Gu, Jinjie Gan, Leilei Zhao, Xiangyu Zhuang, Chenyi Gu, Shi Artificial Intelligence 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. |
| title | FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.24645 |