Metraipolis › archive › dc_fcb9bd0c6acc

SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution — arXiv:2608.18933

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18933
License (as archived)
CC0-1.0
Archived
2026-10-18T13:45:26.406Z
SHA-256 of the archived text
1761ac708ccdc4f1e4afde434a64b78acdd476ed665921b0aa4e33e956c4819d
Stable URL of this page
https://metraipolis.com/documento/dc_fcb9bd0c6acc

How to cite

SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution — arXiv:2608.18933 — arXiv (en), https://arxiv.org/abs/2608.18933 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fcb9bd0c6acc (Metraipolis archive dc_fcb9bd0c6acc, sha256 1761ac708ccdc4f1e4afde434a64b78acdd476ed665921b0aa4e33e956c4819d)
BibTeX
@misc{dcfcb9bd0c6acc,
  title = {SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution — arXiv:2608.18933},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18933},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fcb9bd0c6acc; sha256 1761ac708ccdc4f1e4afde434a64b78acdd476ed665921b0aa4e33e956c4819d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18933. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) based agents have demonstrated remarkable proficiency in automated software issue resolution, yet they often struggle to resolve issues in a specific repository because they lack project-specific knowledge. Existing self-evolving approaches acquire such knowledge from repository history or online repair trajectories, but they either depend on available historical issue-resolution signals or incur substantial per-issue test-time exploration cost. In this paper, we propose SkillForge, a self-distillation framework that proactively acquires project-specific knowledge from the repository itself. Instead of waiting for real issues to expose project-specific knowledge gaps, SkillForge synthesizes project-specific issues by re-implementing test-covered core functionalities of the repository. By resolving these synthetic issues, SkillForge distills reusable project-specific knowledge into entity-grounded skills and associates them with relevant repository entities for future issue resolution. Extensive experiments using both open-source and closed-source models show that SkillForge consistently improves issue resolution performance over strong baselines. These results demonstrate that proactively acquiring project-specific knowledge before solving real issues substantially improves downstream software issue resolution.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.18933 — 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 2026-10-18T13:41:17.984Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).