Metraipolis › archive › dc_4aab4f458445
AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair — arXiv:2609.20130
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20130
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:24:05.450Z
- SHA-256 of the archived text
9a8ee9dc2d8d61b037bcfc4edfff4ff6082233fcc74d8047ead471f3375a15dc- Stable URL of this page
https://metraipolis.com/documento/dc_4aab4f458445
How to cite
AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair — arXiv:2609.20130 — arXiv (en), https://arxiv.org/abs/2609.20130 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4aab4f458445 (Metraipolis archive dc_4aab4f458445, sha256 9a8ee9dc2d8d61b037bcfc4edfff4ff6082233fcc74d8047ead471f3375a15dc)
BibTeX
@misc{dc4aab4f458445,
title = {AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair — arXiv:2609.20130},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20130},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4aab4f458445; sha256 9a8ee9dc2d8d61b037bcfc4edfff4ff6082233fcc74d8047ead471f3375a15dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20130. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent memory-augmented repository-level program repair methods reuse historical repair experiences to improve LLM-based issue resolution. However, our analysis reveals three limitations in existing repository-level memory retrieval. First, episodic memory is highly imbalanced across repositories, leaving low-resource repositories with little effective support. Second, more memory does not monotonically lead to higher repair success, suggesting that relevance, quality, and redundancy matter more than raw memory volume. Third, memory accumulation is phase-misaligned: repositories may contain many reproduction experiences but few patch or refinement experiences. To address these problems, we propose an adaptive experience retrieval framework for repository-level program repair. Our framework introduces coverage-aware retrieval, which falls back to cross-repository or repair-type-based memories when same-repository memory is insufficient; quality-aware selection, which ranks memories by relevance, historical utility, specificity, and redundancy; and stage-aware routing, which separates and retrieves memories for reproduction, localization, patch generation, patch refinement, and validation. Evaluated on SWE-Bench-Lite and SWE-Bench-Verified, the proposed framework improves repair performance on under-covered repositories, reduces noisy memory retrieval, and better supports failed-to-fixed patch refinement. Our results show that the key to memory-augmented repair is not simply accumulating more experiences, but retrieving the right experiences for the right repair context. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.20130 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T03:04:13.908Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).