Agentic Bug Reproduction for Effective Automated Program Repair at Google

TL;DR

This paper presents a novel agent-based approach using a fine-tuned Large Language Model to generate bug reproduction tests from industry bug reports, significantly improving automated debugging and repair at Google.

Contribution

It introduces BRT Agent, an LLM-based method for generating bug reproduction tests, outperforming existing techniques and enhancing automated program repair in a large-scale industrial setting.

Findings

BRT Agent achieves a 28% plausible BRT generation rate, outperforming LIBRO's 10%.

Integrating generated BRTs with APR increases bugs fixed by 30%.

EPR metric effectively selects promising fixes with 70% accuracy in top-1 ranking.

Abstract

Bug reports often lack sufficient detail for developers to reproduce and fix the underlying defects. Bug Reproduction Tests (BRTs), tests that fail when the bug is present and pass when it has been resolved, are crucial for debugging, but they are rarely included in bug reports, both in open-source and in industrial settings. Thus, automatically generating BRTs from bug reports has the potential to accelerate the debugging process and lower time to repair. This paper investigates automated BRT generation within an industry setting, specifically at Google, focusing on the challenges of a large-scale, proprietary codebase and considering real-world industry bugs extracted from Google's internal issue tracker. We adapt and evaluate a state-of-the-art BRT generation technique, LIBRO, and present our agent-based approach, BRT Agent, which makes use of a fine-tuned Large Language Model (LLM) for code editing. Our BRT Agent significantly outperforms LIBRO, achieving a 28% plausible BRT generation rate, compared to 10% by LIBRO, on 80 human-reported bugs from Google's internal issue tracker. We further investigate the practical value of generated BRTs by integrating them with an Automated Program Repair (APR) system at Google. Our results show that providing BRTs to the APR system results in 30% more bugs with plausible fixes. Additionally, we introduce Ensemble Pass Rate (EPR), a metric which leverages the generated BRTs to select the most promising fixes from all fixes generated by APR system. Our evaluation on EPR for Top-K and threshold-based fix selections demonstrates promising results and trade-offs. For example, EPR correctly selects a plausible fix from a pool of 20 candidates in 70% of cases, based on its top-1 ranking.