@inproceedings{sun-etal-2026-training,
    title = "Training Verifier to Assessing Complex Real-World Tool-Use Trajectories",
    author = "Sun, Linzhuang  and
      Chen, Mingyang  and
      Liang, Hao  and
      Li, Tianpeng  and
      Yijie, Zhou  and
      Zhu, Chenzheng  and
      Guo, Tianyu  and
      Zhang, Huanyao  and
      Wei, Jingxuan  and
      Yu, Bihui  and
      Yang, Fan  and
      Zhang, Wentao",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1647/",
    pages = "32922--32936",
    ISBN = "979-8-89176-395-1",
    abstract = "Training effective AI agents for real-world tool-use interactions requires data that faithfully captures the dynamics of human{--}agent collaboration. However, such data is scarce, and existing methods often resort to synthetic data generation. The inherently dynamic and complex nature of user{--}agent interactions makes ensuring data quality particularly challenging. Current verification approaches are typically entangled with the synthesis process itself, resulting in complicated implementations that undermine both reproducibility and scalability. To address this, we introduce Tool-Verifier-7B, a plug-and-play framework for data quality control in tool-use scenarios. Building on this verifier and our data synthesis strategy, we construct the Tool-Verify dataset, which contains 3,295 curated samples. To directly assess verifier performance, we further release Tool-V-Bench, a benchmark of 165 human-validated trajectories spanning diverse interaction complexities. Comprehensive experiments show that Tool-Verifier-7B surpasses Qwen2.5-72B-Instruct on Tool-V-Bench. Moreover, the Tool-Verify dataset achieves superior performance compared to the previous APIGen-MT dataset."
}