Metraipolis › archive › dc_2baeb798d016

ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation — arXiv:2608.04439

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04439
License (as archived): CC0-1.0
Archived: 2026-10-31T11:14:19.448Z
SHA-256 of the archived text: 9f055ffc2bb40452c104d3be3d45cce50cf70a09082b233b875e122acf0cbcb7
Stable URL of this page: https://metraipolis.com/documento/dc_2baeb798d016

How to cite

ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation — arXiv:2608.04439 — arXiv (en), https://arxiv.org/abs/2608.04439 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2baeb798d016 (Metraipolis archive dc_2baeb798d016, sha256 9f055ffc2bb40452c104d3be3d45cce50cf70a09082b233b875e122acf0cbcb7)

BibTeX

@misc{dc2baeb798d016,
  title = {ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation — arXiv:2608.04439},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04439},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2baeb798d016; sha256 9f055ffc2bb40452c104d3be3d45cce50cf70a09082b233b875e122acf0cbcb7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04439. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have made notable progress in code generation, but they still struggle on challenging tasks that require sophisticated algorithms or complex implementations. Recent methods increasingly use code execution as feedback, especially in self-correction pipelines that construct verification signals from generated code. However, these pipelines often depend on supervision signals whose reliability is unknown, which can introduce misleading feedback, unnecessary revisions, and incorrect final answers. To address this issue, we propose ExeCRE, an Execution-Consistency guided code Reliability Estimation framework. Instead of judging candidate code by tests or LLM feedback, ExeCRE estimates code reliability by statistically analyzing consistency patterns in execution outputs over a large number of randomly generated inputs. It collects execution outputs over generated inputs, projects them into consistency signals, and applies the Dawid-Skene model to infer latent code reliability. We integrate ExeCRE into self-correction for code generation. Experiments show that ExeCRE consistently improves both effectiveness and stability, while substantially reducing misleading correction signals. Under GPT-5.2 on LiveCodeBench, the average number of misleading feedback cases on already correct code drops from 113.2 with a representative self-correction baseline to 14.0 with ExeCRE. As an additional study, we apply the same reliability estimation strategy to code-based mathematical reasoning and observe similar benefits. These results suggest that ExeCRE enables more reliable use of generated code in execution-based pipelines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04439 — 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 2026-10-31T11:02:13.511Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).