Metraipolis › archive › dc_13be0aefeb2a
Learning Globally Reusable Skills for Coding Agents — arXiv:2608.06153
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.06153
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:04:56.752Z
- SHA-256 of the archived text
e669d445871e589f3960179b4a6c032dde10551d09c0f4bd01774b3ec4219c7e- Stable URL of this page
https://metraipolis.com/documento/dc_13be0aefeb2a
How to cite
Learning Globally Reusable Skills for Coding Agents — arXiv:2608.06153 — arXiv (en), https://arxiv.org/abs/2608.06153 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_13be0aefeb2a (Metraipolis archive dc_13be0aefeb2a, sha256 e669d445871e589f3960179b4a6c032dde10551d09c0f4bd01774b3ec4219c7e)
BibTeX
@misc{dc13be0aefeb2a,
title = {Learning Globally Reusable Skills for Coding Agents — arXiv:2608.06153},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.06153},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_13be0aefeb2a; sha256 e669d445871e589f3960179b4a6c032dde10551d09c0f4bd01774b3ec4219c7e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06153. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without expensive retraining. However, existing approaches typically treat skill evolution as a sequence of local updates, overlooking relationships among skills and often producing overfitted skill updates that fail to generalize across tasks. We propose GSE, a globalized skill evolution framework that jointly optimizes skill compatibility and skill generalization. To preserve consistency across the skill bank, GSE maintains a Skill Relation Graph (SRG) that explicitly models and co-evolves inter-skill relationships. To improve generalization, GSE performs cluster-based skill consolidation to abstract reusable capabilities from local updates and employs replay-driven verification to prevent overfitting and behavioral regressions. We evaluate GSE on two representative software engineering tasks: bug-revealing test generation and false-positive bug report filtering. Across two state-of-the-art coding agents, OpenHands and mini-SWE-agent, GSE consistently achieves the best precision, recall, and F1-score. Compared with existing evolution techniques, GSE improves precision and recall by 6.1%~34.1% and 31.8%~180.0% for test generation, and by 15.4%~96.4% and 13.1%~19.8% for false-positive filtering. Deployment on an internal industrial agent further yields a 61.4% improvement in F1-score, demonstrating the effectiveness and generalizability of GSE for evolving effective skills. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-07 in cs.SE). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.06153 — 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 2026-10-27T07:55:47.051Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).