@inproceedings{zhang-etal-2025-toolexpnet,
    title = "{T}ool{E}xp{N}et: Optimizing Multi-Tool Selection in {LLM}s with Similarity and Dependency-Aware Experience Networks",
    author = "Zhang, Zijing  and
      Chen, Zhanpeng  and
      Zhu, He  and
      Chen, Ziyang  and
      Du, Nan  and
      Li, Xiaolong",
    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/ingestion-acl-25/2025.findings-acl.811/",
    pages = "15706--15722",
    ISBN = "979-8-89176-256-5",
    abstract = "Tool learning enhances Large Language Models' (LLMs) dynamic interaction with external tools, improving their ability to solve complex problems. However, current empirical methods, which primarily focus on isolated tools learning, still struggle with accurate multi-tool selection due to issues like confusing similar tools and neglecting dependencies. To address these challenges, we propose the Tool Experience Network (ToolExpNet), which integrates tools and trial-and-error experiences into a network characterized by semantic similarity and dependency relationships. ToolExpNet iteratively conducts simulated experiments using adaptive sampling to explore subtle differences and connections between tools, and summarizes these experiences to provide insightful guidance for LLM tool selection. Our experiments demonstrate that learning the relationships between tools helps achieve more comprehensive tool learning. Evaluations on multiple real-world API datasets show that ToolExpNet effectively addresses common challenges in multi-tool selection, significantly outperforming existing baselines across different foundation LLMs."
}