Automated Program Repair: Emerging Trends Pose and Expose Problems for Benchmarks

Created by W.Langdon from gp-bibliography.bib Revision:1.9209

@Article{Renzullo:2025:ACMComputSurv,

• author = "Joseph Renzullo and Pemma Reiter and Westley Weimer and Stephanie Forrest",
• title = "Automated Program Repair: Emerging Trends Pose and Expose Problems for Benchmarks",
• journal = "ACM Computing Surveys",
• year = "2025",
• volume = "57",
• number = "8",
• pages = "Article 208",
• month = mar,
• keywords = "genetic algorithms, genetic programming, genetic improvement, automated program repair, APR, SBSE, Maintaining software, machine learning, AI, LLM, benchmarks, patch quality, Standup4NPR, GenProg, ARJA, APR-COMP 2024",
• ISSN = "0360-0300",
• DOI = "10.1145/3704997",
• size = "18 pages",
• abstract = "...we review work in APR published in the fields top five venues since 2018, emphasizing emerging trends in the field, including the dramatic rise of ML models, including LLMs. ML-based articles are categorized along structural and functional dimensions, and a variety of issues are identified that these new methods raise. Importantly, data leakage and contamination concerns arise from the challenge of validating ML-based APR using existing benchmarks, which were designed before these techniques were popular. We discuss inconsistencies in evaluation design and performance reporting and offer pointers to solutions where they are available. Finally, we highlight promising new directions that the field is already taking.",

}

Genetic Programming entries for Joseph Renzullo Pemma D Reiter Westley Weimer Stephanie Forrest

Citations