# Graph of Trace: Visualizing Execution Traces of Scientific Agent

arXiv: https://arxiv.org/abs/2606.15116 · HTML: https://mlsanity.com/paper/2606.15116/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2026.

## Built on by (most cited first, 4 of 4)

- [LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents](https://mlsanity.com/paper/2608.18398/) (2026)
- [BrainPilot: Automating Brain Discovery with Agentic Research](https://mlsanity.com/paper/2607.15079/) (2026)
- [Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science](https://mlsanity.com/paper/2607.13220/) (2026)
- [Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers](https://mlsanity.com/paper/2609.01466/) (2026)

## Abstract (arXiv)

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.