ICSE 2026 (series) / GI 2026 (series) / Genetic Improvement 2026 /
Applying Genetic Improvement Techniques for Automated Program Repair of Transpiled Code
We use Genetic Improvement (GI)-based Automated Program Repair (APR) techniques for syntax correction on transpiled code produced by both large language models (LLMs) and rule-based translators. LLM-assisted Type Change Operator and Boolean Value Change Operator were added to Magpie, which reduced transpilation bugs from Python to Java by 33% (LLM) and by 18% on rule-based translations.
| [Presentation] Applying Genetic Improvement Techniques for Automated Program Repair of Transpiled Code (GI_Transpilation_Repair_Presentation.pdf) | 271KiB |
Mon 13 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change
Mon 13 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change
11:00 - 12:30 | |||
11:00 30mTutorial | Mini-Tutorial: Automated Software Improvement with Magpie GI Aymeric Blot University of Rennes, IRISA / INRIA File Attached | ||
11:30 20mTalk | Applying Genetic Improvement Techniques for Automated Program Repair of Transpiled Code GI Prasham Jadhwani University College London (UCL), Carol Hanna University College London, William Langdon University College London, Justyna Petke University College London DOI Pre-print Media Attached File Attached | ||
11:50 20mTalk | GI-Agent Search-Based LLM Agent for Code Optimization with Genetic Improvement GI Donghyun Lee University College London, William Langdon University College London, Justyna Petke University College London DOI Pre-print Media Attached File Attached | ||
12:10 15mTalk | Databending as a Target for Genetic Improvement GI Erik Fredericks Grand Valley State University, Byron DeVries Grand Valley State University, Reihaneh Hariri Grand Valley State University Pre-print Media Attached File Attached | ||
12:25 5mDay closing | Closing GI | ||