Academic Journal

ReproCopilot: LLM-Driven Failure Reproduction with Dynamic Refinement

Bibliographic Details
Title: ReproCopilot: LLM-Driven Failure Reproduction with Dynamic Refinement
Authors: Tanakorn Leesatapornwongsa, Fazle Faisal, Suman Nath
Source: Proceedings of the ACM on Software Engineering. 2:2920-2943
Publisher Information: Association for Computing Machinery (ACM), 2025.
Publication Year: 2025
Description: Failure reproduction is a crucial step for debugging software systems, but it is often challenging and time-consuming, especially when the failures are caused by complex inputs, states, or environments. In this paper, we present ReproCopilot, a tool that leverages program analysis and a large language model (LLM) to generate a workload (i.e., code and inputs) that can reproduce a given failure. ReproCopilot proposes two novel techniques: state-oriented code generation and dynamic refinement. These techniques can iteratively guide the LLM with program analysis feedback until the generated workload can successfully reproduce the target failure. We evaluate ReproCopilot on 50 real-world failures from 17 open-source projects, and show that it can reproduce 76% of them, significantly outperforming the-state-of-the-art solutions.
Document Type: Article
Language: English
ISSN: 2994-970X
DOI: 10.1145/3729399
Accession Number: edsair.doi...........b16d8466d64794e7f6ef4d0a09c565db
Database: OpenAIRE
Description
ISSN:2994970X
DOI:10.1145/3729399