How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on tau-bench

Venkatesh Mishra, Amir Saeidi, Satyam Raj, Mutsumi Nakamura, Gaowen Liu, Ali Payani, Jayanth Srinivasa, Chitta Baral


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 𝜏‐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^5 scores. These findings highlight the superior reliability and consistency of IRMA compared to other methods in dynamic environments.
Anthology ID:
2025.findings-emnlp.1250
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22949–22972
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1250/
DOI:
Bibkey:
Cite (ACL):
Venkatesh Mishra, Amir Saeidi, Satyam Raj, Mutsumi Nakamura, Gaowen Liu, Ali Payani, Jayanth Srinivasa, and Chitta Baral. 2025. How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on tau-bench. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 22949–22972, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on tau-bench (Mishra et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1250.pdf
Checklist:
 2025.findings-emnlp.1250.checklist.pdf