# TraceView: Interactive Visualization of Agentic Program Repair Trajectories

arXiv: https://arxiv.org/abs/2606.22110 · HTML: https://mlsanity.com/paper/2606.22110/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 24 references that are in the map.
- First posted on arXiv 20 Jun 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 20 of 20)

- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories](https://mlsanity.com/paper/2506.18824/) (2025)
- [Automated Repair of Programs from Large Language Models](https://mlsanity.com/paper/2205.10583/) (2022)
- [Interactive Debugging and Steering of Multi-Agent AI Systems](https://mlsanity.com/paper/2503.02068/) (2025)
- [Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning](https://mlsanity.com/paper/2302.04732/) (2023)
- [Process-Centric Analysis of Agentic Software Systems](https://mlsanity.com/paper/2512.02393/) (2025)
- [AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems](https://mlsanity.com/paper/2402.08995/) (2024)
- [Wink: Recovering from Misbehaviors in Coding Agents](https://mlsanity.com/paper/2602.17037/) (2026)
- [AgentStepper: Interactive Debugging of Software Development Agents](https://mlsanity.com/paper/2602.06593/) (2026)
- [SeaView: Software Engineering Agent Visual Interface for Enhanced Workflow](https://mlsanity.com/paper/2504.08696/) (2025)
- [What Characteristics Make ChatGPT Effective for Software Issue Resolution? An Empirical Study of Task, Project, and Conversational Signals in GitHub Issues](https://mlsanity.com/paper/2506.22390/) (2025)
- [Hierarchical Knowledge Injection for Improving LLM-based Program Repair](https://mlsanity.com/paper/2506.24015/) (2025)
- [Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation](https://mlsanity.com/paper/2512.00215/) (2025)
- [Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement](https://mlsanity.com/paper/2508.12555/) (2025)
- [ReTrace: Interactive Visualizations for Reasoning Traces of Large Reasoning Models](https://mlsanity.com/paper/2511.11187/) (2025)
- [Anteater: Interactive Visualization of Program Execution Values in Context](https://mlsanity.com/paper/1907.02872/) (2019)
- [InconLens: Interactive Visual Diagnosis of Behavioral Inconsistencies in LLM-based Agentic Systems](https://mlsanity.com/paper/2603.28106/) (2026)

## Built on by (most cited first, 2 of 2)

- [Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?](https://mlsanity.com/paper/2607.28871/) (2026)
- [AgentPProf: Semantic Profiler for Long Horizon AI Agents](https://mlsanity.com/paper/2609.20301/) (2026)

## Abstract (arXiv)

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.