@inproceedings{gao-etal-2026-graph,
    title = "Graph of Trace: Visualizing Execution Traces of Scientific Agents",
    author = "Gao, Tianci  and
      Li, Haoxuan  and
      Li, Jian He  and
      Zhao, Tianxiang  and
      Runze, Shi  and
      Wang, Weiran  and
      Wu, Zezhao  and
      Mi, Lu",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.29/",
    pages = "297--306",
    ISBN = "979-8-89176-392-0",
    abstract = "Scientific AI agents can autonomously carry out complex research workflows, yet these unfolded workflows often remains difficult for humans to inspect and review, limiting interpretable, controllable and effective human{--}AI collaboration. To address this challenge, we present a monitoring and visualization framework that records fine-grained execution events and organizes them into a directed graph that make agent workflows explicit as they proceed. The system records intermediate steps (e.g. tool calls and code executions), and renders them as real-time updated visual traces that expose workflow structure. This allows users to examine how results are produced, identify where failures emerge, and better understand agent behavior across different stages of the research process.We conduct an evaluation on complex research tasks with domain experts of interdisciplinary background in AI, neuroscience and biology. Experts report that structured traces visualization improves understanding of agent workflows, perceived interpretability, and usability for analysis and further interaction."
}