Graph of Trace: Visualizing Execution Traces of Scientific Agent
For researchers and developers of scientific AI agents, this addresses the challenge of inspecting complex agent workflows, but the contribution is incremental as it applies existing visualization techniques to a new domain.
The paper presents a framework that records execution traces of scientific AI agents as directed graphs, enabling real-time visualization of agent workflows. Domain experts reported improved understanding, interpretability, and usability for analysis.
Scientific AI agents can autonomously carry out complex research workflows, yet these unfolded workflows often remain 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 makes 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 backgrounds 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.