Agent Trajectory Explorer: Visualizing and Providing Feedback on Agent Trajectories
Abstract
Agentic systems interleave large language model (LLM) reasoning, tool usage, and tool observations over multiple iterations to tackle complex tasks. The raw data from an agent's problem-solving process (the agents' trajectory) is not an ideal format for human analysis and oversight. There is a need for tooling that converts this primary data into an easily navigable and understandable visual format for better human feedback. To address this opportunity, we developed the Agent Trajectory Explorer, a tool designed to help AI developers and researchers visualize, annotate, and demonstrate agent behavior.
Cite
Text
Desmond et al. "Agent Trajectory Explorer: Visualizing and Providing Feedback on Agent Trajectories." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35350Markdown
[Desmond et al. "Agent Trajectory Explorer: Visualizing and Providing Feedback on Agent Trajectories." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/desmond2025aaai-agent/) doi:10.1609/AAAI.V39I28.35350BibTeX
@inproceedings{desmond2025aaai-agent,
title = {{Agent Trajectory Explorer: Visualizing and Providing Feedback on Agent Trajectories}},
author = {Desmond, Michael and Lee, Ja Young and Ibrahim, Ibrahim and Johnson, James M. and Sil, Avirup and MacNair, Justin and Puri, Ruchir},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {29634-29636},
doi = {10.1609/AAAI.V39I28.35350},
url = {https://mlanthology.org/aaai/2025/desmond2025aaai-agent/}
}