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

arXiv: https://arxiv.org/abs/2506.10484 · HTML: https://mlsanity.com/paper/2506.10484/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2025.

## Built on by (most cited first, 30 of 35)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems](https://mlsanity.com/paper/2507.02097/) (2025)
- [AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library](https://mlsanity.com/paper/2510.18428/) (2025)
- [Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents](https://mlsanity.com/paper/2602.07900/) (2026)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [Structurally Aligned Subtask-Level Memory for Software Engineering Agents](https://mlsanity.com/paper/2602.21611/) (2026)
- [MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences](https://mlsanity.com/paper/2601.06789/) (2026)
- [SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair](https://mlsanity.com/paper/2602.23647/) (2026)
- [A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks](https://mlsanity.com/paper/2511.00872/) (2025)
- [InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution](https://mlsanity.com/paper/2511.16004/) (2025)
- [TDFlow: Agentic Workflows for Test Driven Development](https://mlsanity.com/paper/2510.23761/) (2025)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair](https://mlsanity.com/paper/2603.01048/) (2026)
- [MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback](https://mlsanity.com/paper/2606.07909/) (2026)
- [HAFixAgent: History-Aware Program Repair Agent](https://mlsanity.com/paper/2511.01047/) (2025)
- [InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution](https://mlsanity.com/paper/2511.16005/) (2025)
- [From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair](https://mlsanity.com/paper/2601.23257/) (2026)
- [FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards](https://mlsanity.com/paper/2606.06960/) (2026)
- [LLM Agents Can See Code Repositories](https://mlsanity.com/paper/2606.14061/) (2026)
- [Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair](https://mlsanity.com/paper/2606.30963/) (2026)
- [ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localization](https://mlsanity.com/paper/2605.03117/) (2026)
- [Self-Evolving Coding Agents](https://mlsanity.com/paper/2608.03392/) (2026)
- [SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution](https://mlsanity.com/paper/2608.18933/) (2026)
- [SIADAFIX: issue description response for adaptive program repair](https://mlsanity.com/paper/2510.16059/) (2025)
- [Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation](https://mlsanity.com/paper/2605.14563/) (2026)
- [Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench](https://mlsanity.com/paper/2605.15226/) (2026)
- [ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair](https://mlsanity.com/paper/2607.01916/) (2026)
- [Writing Bug Reports for Software Repair Agents: What Information Matters Most?](https://mlsanity.com/paper/2607.09553/) (2026)
- [Reusing Past Repairs Through Hierarchical Trajectory Abstraction for Coding Agents](https://mlsanity.com/paper/2607.29658/) (2026)
- [Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution](https://mlsanity.com/paper/2608.06811/) (2026)

## Abstract (arXiv)

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. Specifically, ExpeRepair organizes prior repair knowledge into two complementary memories: an episodic memory that stores concrete repair demonstrations, and a semantic memory that encodes abstract, reflective insights. At inference time, ExpeRepair activates both memory systems by retrieving relevant demonstrations from episodic memory and recalling high-level repair insights from semantic memory. It further enhances adaptability through dynamic prompt composition, integrating both memory types to replace static prompts with context-aware, experience-driven prompts. We evaluate ExpeRepair on two benchmarks: SWE-Bench Lite and SWE-Bench Verified. Experimental results show that ExpeRepair achieves pass@1 scores of 60.3% and 74.6% on the two benchmarks, respectively, achieving the best performance among the evaluated open-source methods. We have open-sourced ExpeRepair at https://github.com/ExpeRepair/ExpeRepair.