Towards Automating the AI Operations Lifecycle
Matthew Arnold, Jeffrey Boston, et al.
MLSys 2020
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.
Matthew Arnold, Jeffrey Boston, et al.
MLSys 2020
Dakuo Wang, Liuping Wang, et al.
CHI 2021
Juliana Jansen Ferreira, Vinicius Segura, et al.
ACS Spring 2025
Fernando Martinez, Juntao Chen, et al.
AAAI 2025