@inproceedings{wu-etal-2025-art,
    title = "The Art of Tool Interface Design",
    author = "Wu, Yunnan  and
      Chen, Qile P.  and
      Baranwal, Deshank  and
      Zhou, Jinlong  and
      Yuan, Jian",
    editor = "Kamalloo, Ehsan  and
      Gontier, Nicolas  and
      Lu, Xing Han  and
      Dziri, Nouha  and
      Murty, Shikhar  and
      Lacoste, Alexandre",
    booktitle = "Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.realm-1.5/",
    doi = "10.18653/v1/2025.realm-1.5",
    pages = "63--79",
    ISBN = "979-8-89176-264-0",
    abstract = "We present an agentic framework, Thinker, which achieves state of art performance in challenging reasoning tasks for realistic customer service scenarios that involve complex business logic and human interactions via long horizons. On the $\tau$-bench retail dataset, Thinker achieves 82.6{\%} success rate with GPT-4o (version 2024-06-01) (baseline: 68.3{\%}), and 81.9{\%} success rate with Llama-3.1 405B (baseline: 49.6{\%}), without any fine-tuning. Thinker effectively closes the gap in reasoning capabilities between the base models by introducing proper structure.The key features of the Thinker framework are: (1) State-Machine Augmented Generation (SMAG), which represents business logic as state machines and the LLM uses state machines as tools. (2) Delegation of tasks from the main reasoning loop to LLM-powered tools.(3) Adaptive context management.Our prompting-only solution achieves signficant gains, while still maintaining a simple and standard agentic architecture with a ReAct style reasoning loop. The key is to innovate on the tool interface design, as exemplified by SMAG and the LLM-powered tools."
}