Metraipolis › archive › dc_46fe04a2b754
Self-Evolving Coding Rules for AI Coding Agents — arXiv:2610.00650
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00650
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:10:32.853Z
- SHA-256 of the archived text
14be2ad8fc42781935d1e50d212c068db19fd7bfc525a6d6e50b2aa7a13fe4d2- Stable URL of this page
https://metraipolis.com/documento/dc_46fe04a2b754
How to cite
Self-Evolving Coding Rules for AI Coding Agents — arXiv:2610.00650 — arXiv (en), https://arxiv.org/abs/2610.00650 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46fe04a2b754 (Metraipolis archive dc_46fe04a2b754, sha256 14be2ad8fc42781935d1e50d212c068db19fd7bfc525a6d6e50b2aa7a13fe4d2)
BibTeX
@misc{dc46fe04a2b754,
title = {Self-Evolving Coding Rules for AI Coding Agents — arXiv:2610.00650},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00650},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46fe04a2b754; sha256 14be2ad8fc42781935d1e50d212c068db19fd7bfc525a6d6e50b2aa7a13fe4d2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00650. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The performance of AI coding agents is highly dependent on their underlying coding rules. However, existing coding rules are typically hand-crafted and fixed, making the process labor-intensive and often suboptimal. In this work, we propose RuleEvolve, a self-evolving framework for coding rules. RuleEvolve maintains a pool of candidate coding rules and iteratively improves them. In each iteration, it employs an LLM-powered mutator module to generate variants from existing candidates, and then uses a judge module to evaluate these variants and update the pool with the best-performing ones. Extensive evaluations across two coding-agent frameworks, four backbone LLMs, and three benchmarks demonstrate that RuleEvolve outperforms both manual engineering and existing prompt optimization baselines in terms of functional correctness of the generated code, code length, and/or generation cost (e.g., tokens used). Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.00650 — 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 2026-10-06T10:21:28.096Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).