Metraipolis › archive › dc_19f64b401b96
WiseSpec: Requirements-Driven Agents for Code Generation — arXiv:2609.00568
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00568
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:33:30.180Z
- SHA-256 of the archived text
79a37516cca58c6910da6823d7c46d56d4503f63d4de9631153fc461d4efd367- Stable URL of this page
https://metraipolis.com/documento/dc_19f64b401b96
How to cite
WiseSpec: Requirements-Driven Agents for Code Generation — arXiv:2609.00568 — arXiv (en), https://arxiv.org/abs/2609.00568 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19f64b401b96 (Metraipolis archive dc_19f64b401b96, sha256 79a37516cca58c6910da6823d7c46d56d4503f63d4de9631153fc461d4efd367)
BibTeX
@misc{dc19f64b401b96,
title = {WiseSpec: Requirements-Driven Agents for Code Generation — arXiv:2609.00568},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00568},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19f64b401b96; sha256 79a37516cca58c6910da6823d7c46d56d4503f63d4de9631153fc461d4efd367},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00568. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Code generation aims to automatically generate source code from task requirements and has attracted significant attention with the rapid advancement of large language models (LLMs). Despite remarkable progress, LLMs often struggle to generate correct code for complex software engineering tasks because task descriptions are frequently incomplete, ambiguous, or lack critical contextual information. Existing approaches primarily improve the capabilities of coding agents through more sophisticated tools, skills, and workflows, while largely overlooking the quality of the task requirements themselves. To address this limitation, we draw inspiration from software requirements engineering and propose WiseSpec, a novel requirements-driven agent framework for repository-level code generation. WiseSpec automatically constructs structured and information-rich requirements, assesses their quality through execution-based evaluation, and iteratively refines them to better guide code generation. Experimental results show that WiseSpec consistently outperforms all baselines, achieving an average improvement of 13.17% in %Resolved. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.00568 — 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 2026-10-17T06:15:12.800Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).