Search papers, labs, and topics across Lattice.
This paper introduces EvolRepair, a population-based semantic evolution framework that leverages LLMs for automated program repair. EvolRepair organizes candidate repairs into behaviorally coherent groups, enabling diversity preservation and recombination of complementary repair insights. Experiments demonstrate that EvolRepair significantly outperforms existing LLM-based LLM-based APR approaches by using structured failure patterns to guide search and refine repair strategies.
LLMs can fix more bugs when guided by a semantic evolutionary algorithm that recombines successful partial fixes across a population of candidate repairs.
Large language models (LLMs) have recently shown strong potential for automated program repair (APR), particularly through iterative refinement that generates and improves candidate patches. However, state-of-the-art iterative refinement LLM-based APR approaches cannot fully address challenges, including maintaining useful diversity among repair hypotheses, identifying semantically related repair families, composing complementary partial fixes, exploiting structured failure information, and escaping structurally flawed search regions. In this paper, we propose a Population-Based Semantic Evolution framework for APR iterative refinement, called EvolRepair, that formulates LLM-based APR as a semantic evolutionary algorithm. EvolRepair reformulates the search paradigm of classic genetic algorithm for APR, but replaces its syntax-based operators with semantics-aware components powered by LLMs and structured execution feedback. Candidate repairs are organized into behaviorally coherent groups, enabling the algorithm to preserve diversity, reason over repair families, and synthesize stronger candidates by recombining complementary repair insights across the population. By leveraging structured failure patterns to guide search direction, EvolRepair can both refine promising repair strategies and shift toward alternative abstractions when necessary. Our experiments show that EvolRepair substantially improves repair effectiveness over existing LLM-based APR approaches.
