EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair

Understand

Automatically repairing software issues remains a fundamental challenge at the intersection of software engineering and AI.

• Although recent advances in Large Language Models (LLMs) have demonstrated potential for repository-level repair tasks, current methods exhibit two notable limitations: (1) they often address issues in isolation, neglecting to incorporate insights from previously resolved issues, and (2) they rely on static, rigid prompting strategies that constrain their ability to generalize across diverse and evolving contexts.
• We propose ExpeRepair, a novel LLM-based program repair framework inspired by the dual-memory systems of human cognition, where episodic and semantic memory synergistically support learning and decision-making.
• Unlike existing methods, ExpeRepair continuously learns from historical repair experiences via dual-channel knowledge accumulation, enabling it to adaptively reuse past knowledge during inference.