AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair
Source
Z. C. Luo, J. C. Guo, W. J. He, S. Y. Wang, J. C. Yu, F. M. Zhao, Y. Chen, T. Cao, L. Q. Liu, N. Zheng, W. Xu, J. Jiang, Z. M. Zhao
Author
Z. C. Luo, J. C. Guo, W. J. He, S. Y. Wang, J. C. Yu, F. M. Zhao, Y. Chen, T. Cao, L. Q. Liu, N. Zheng, W. Xu, J. Jiang, Z. M. Zhao
Date
Key takeaways · AI-distilled
Analysis of memory-augmented program repair found more stored repair experience doesn't reliably improve success -- relevance, quality, and redundancy of retrieved memories matter more than raw volume.
Memory is also phase-misaligned: repos often accumulate many bug-reproduction experiences but far fewer patch-generation or patch-refinement ones, leaving later repair stages under-supported.
AdaRepair-Mem's coverage-aware retrieval falls back to cross-repository or repair-type memories when a repo's own history is too thin, helping low-resource repositories that otherwise get little support.
On SWE-benchThe standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.Full definition →-Lite and SWE-Bench-Verified, the framework improved repair on under-covered repositories and better supported turning failed patches into fixed ones.
Terms in this piece · Glossary
alignment — The work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
SWE-bench — The standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.
Why it matters
More historical repair experience doesn't reliably improve AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → success; retrieval quality and coverage matter more than volume, a concrete lesson for memory-augmented repair systems.
articleRethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiencyJunchi Liu, Ali Bigdeli, Roya Daneshi, Atu Ambala, Sudipto Ghosh, Fabio Santos
articleRefine After Generation: Toward Correct and Concise Patches in LLM-based Program RepairWenqiang Luo, Jacky Keung, Xiaoyu Shi, Yicheng Sun, Boyang Yang, Zhou Yang, Haoye Tian
articleTemporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub FixesNeeraj Yadav