Graphectory Viewer: A Tool for Process-Centric Analysis of Agentic Software Trajectories
Source
arxiv.org
Author
Charlie Jyu, Shuyang Liu, Reyhaneh Jabbarvand
Date
Why it matters
Comparing successful and failed runs at the level of behavioral phases is how you find out why an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → fails, and there is very little tooling for it.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
articleAgentLogs: A Dataset for Opening the Black Box of GitHub's Cloud AgentJonan Richards, Kosei Horikawa, Youmei Fan, Yutaro Kashiwa, Mairieli Wessel
articleOpenDiscoveryTrace: Process Traces for Evaluating AI Scientist WorkflowsAayam Bansal, Keertan Balaji
articleGeneration of Web Apps with Agentic IDEs: An Empirical AssessmentManuel Marceca, Maria Teresa Rossi, Leonardo Mariani