@inproceedings{mishra-etal-2025-input,
    title = "How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on tau-bench",
    author = "Mishra, Venkatesh  and
      Saeidi, Amir  and
      Raj, Satyam  and
      Nakamura, Mutsumi  and
      Liu, Gaowen  and
      Payani, Ali  and
      Srinivasa, Jayanth  and
      Baral, Chitta",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1250/",
    doi = "10.18653/v1/2025.findings-emnlp.1250",
    pages = "22949--22972",
    ISBN = "979-8-89176-335-7",
    abstract = "Recent advances in reasoning and planning capabilities of large language models (LLMs) have enabled their potential as autonomous agents capable of tool use in dynamic environments. However, in multi-turn conversational environments like $\tau${-}bench, these agents often struggle with consistent reasoning, adherence to domain-specific policies, and extracting correct information over a long horizon of tool-calls and conversation. To capture and mitigate these failures, we conduct a comprehensive manual analysis of the common errors occurring in the conversation trajectories. We then experiment with reformulations of inputs to the tool-calling agent for improvement in agent decision making. Finally, we propose the Input-Reformulation Multi-Agent (IRMA) framework, which automatically reformulates user queries augmented with relevant domain rules and tool suggestions for the tool-calling agent to focus on. The results show that IRMA significantly outperforms ReAct, Function Calling, and Self-Reflection by 16.1{\%}, 12.7{\%}, and 19.1{\%}, respectively, in overall pass{\textasciicircum}5 scores. These findings highlight the superior reliability and consistency of IRMA compared to other methods in dynamic environments."
}