Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ceka, Ira, Mitchell, Hailie, Pujar, Saurabh, Buratti, Luca, Ramji, Shyam, Yang, Junfeng, Kaiser, Gail, Ray, Baishakhi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911722153967616
author Ceka, Ira
Mitchell, Hailie
Pujar, Saurabh
Buratti, Luca
Ramji, Shyam
Yang, Junfeng
Kaiser, Gail
Ray, Baishakhi
author_facet Ceka, Ira
Mitchell, Hailie
Pujar, Saurabh
Buratti, Luca
Ramji, Shyam
Yang, Junfeng
Kaiser, Gail
Ray, Baishakhi
contents Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning, planning, and tool use. Despite impressive leaderboard gains on benchmarks such as SWE-bench, little is understood about how these agents take actions, where they fail, and how their behavior compares to that of human developers. This paper presents the first systematic analysis of five state-of-the-art APR agents across 500 real-world repair tasks, tracing their full decision-making pipelines -- from issue description to patch validation. Our study reveals that while agents excel at simple fixes, they struggle with logic-intensive bugs, often producing verbose or overfitted patches that merely satisfy existing tests. We find that test generation and regression test selection remain major bottlenecks, with agents frequently failing to reproduce issues or run relevant regression tests. Moreover, most agents operate with primitive tooling (e.g., bash scripts) and lack access to debuggers or program analyzers, which constrains their reasoning and patch quality. These findings highlight key limitations in current APR systems and motivate a shift-left approach -- emphasizing early, high-quality test generation and validation -- to reduce spurious fixes and improve semantic correctness. We further outline concrete directions for next-generation APR design: (1) richer and more integrated tool ecosystems, (2) diversified agentic architectures that combine complementary strengths, and (3) benchmarks that prioritize semantic repair quality and test generation fidelity over surface-level success metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08311
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study
Ceka, Ira
Mitchell, Hailie
Pujar, Saurabh
Buratti, Luca
Ramji, Shyam
Yang, Junfeng
Kaiser, Gail
Ray, Baishakhi
Software Engineering
Artificial Intelligence
Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning, planning, and tool use. Despite impressive leaderboard gains on benchmarks such as SWE-bench, little is understood about how these agents take actions, where they fail, and how their behavior compares to that of human developers. This paper presents the first systematic analysis of five state-of-the-art APR agents across 500 real-world repair tasks, tracing their full decision-making pipelines -- from issue description to patch validation. Our study reveals that while agents excel at simple fixes, they struggle with logic-intensive bugs, often producing verbose or overfitted patches that merely satisfy existing tests. We find that test generation and regression test selection remain major bottlenecks, with agents frequently failing to reproduce issues or run relevant regression tests. Moreover, most agents operate with primitive tooling (e.g., bash scripts) and lack access to debuggers or program analyzers, which constrains their reasoning and patch quality. These findings highlight key limitations in current APR systems and motivate a shift-left approach -- emphasizing early, high-quality test generation and validation -- to reduce spurious fixes and improve semantic correctness. We further outline concrete directions for next-generation APR design: (1) richer and more integrated tool ecosystems, (2) diversified agentic architectures that combine complementary strengths, and (3) benchmarks that prioritize semantic repair quality and test generation fidelity over surface-level success metrics.
title Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2506.08311