@inproceedings{liang-etal-2025-tool,
    title = "Tool learning via Inference-time Scaling and Cycle Verifier",
    author = "Liang, Xiaobo  and
      Xie, Wenjin  and
      Li, Juntao  and
      Wang, Wanfu  and
      Chen, Yibin  and
      Chen, Kehai  and
      Zhang, Min",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.1266/",
    pages = "24658--24671",
    ISBN = "979-8-89176-256-5",
    abstract = "In inference-time scaling, Chain-of-Thought (CoT) plays a crucial role in enabling large language models (LLMs) to exhibit reasoning capabilities. However, in many scenarios, high-quality CoT data is scarce or even unavailable. In such cases, STaR-like methods can help LLMs synthesize CoT based on user queries and response, but they inevitably suffer from the risk of compounding errors. In this work, we tackle an even more challenging scenario: tool learning in the absence of user queries. We design a data scaling method using back-translation, which establishes an inference cycle to synthesize both user queries and CoT data. To reudce the compounding error of inference time, we introduce two rule-based verifiers to assess the validity of the synthesized CoT data. In particular, the Cycle Verifier facilitates performance improvement by continuously accumulating new data over multiple iterations. Our approach achieves a \textbf{75.4{\%}} pass rate and a \textbf{79.6{\%}} win rate using small models (7B) in StableToolBench. Notably, these results are obtained exclusively from self-synthesized high-quality data, without relying on external supervision or expert trajectories for warm-up."
}