TraceView: Interactive Visualization of Agentic Program Repair Trajectories

2026-06-20

AI Summary

This work addresses the limited interpretability of large language model–driven automated program repair, which hinders diagnosis and reproducibility of failure cases. To this end, we present TraceView, the first interactive visualization tool that structures repair trajectories into Thought-Action-Result triplets and supports semantic relationship annotation. By integrating trajectory parsing, relational modeling, and graph-based visualization techniques, TraceView enables traceable analysis from high-level overviews to fine-grained details. A user study demonstrates that TraceView significantly enhances developers’ comprehension of the repair process and improves navigation efficiency. The implementation and a demonstration video are publicly available.

Abstract

LLM-based automated program repair (APR) agents generate patches to fix software bugs with minimal human intervention. These agents often produce long trajectories of reasoning, tool use, and feedback to produce candidate patches. Final patch outcomes show whether a repair attempt succeeded or failed, but they do not show how the agent reached that outcome, or where the process became repetitive or misaligned with the task. This makes agentic repair failures difficult to diagnose, reproduce, and prevent. To help developers address these challenges, we present TraceView, an interactive tool for labeling and visualizing repair trajectories from APR systems. TraceView organizes raw and pre-labeled agentic runs with Thought, Action, and Result components to support semantic relation labeling and diagnosis, and renders the resulting trajectory as graph views. Furthermore, TraceView provides relation filters, patch outcome summaries, metrics, and node-level evidence panels to help users inspect how reasoning, actions, and feedback connect across the various steps of an agentic repair attempt. We evaluate TraceView with five researchers through a survey-based user study. Participants reported that TraceView made trajectories easier to scan and that its overview-to-detail workflow helped them better understand repair behavior. The TraceView source code is available at https://github.com/SOAR-Lab/agent-traj-visualization. A screencast of TraceView is available at https://youtu.be/9ZCh7Ifj2AQ.

Problem

• automated program repair
• LLM-based agents
• repair trajectories
• failure diagnosis
• interactive visualization

Innovation

• interactive visualization
• program repair trajectories
• agentic reasoning
• semantic relation labeling
• LLM-based APR