English(EN) Function-Level Execution Feedback for Code Preference Optimization

新框架STEP-KTODER通过函数级反馈优化代码生成

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-26 04:00

研究人员推出了一种名为STEP-KTODER的新型框架，旨在通过函数级过程监督来增强代码生成模型。该方法将“步骤”定义为分解程序中的模块级函数，并利用自动生成的单元测试来分配二进制正确性标签。通过结合函数级监督和结果级反馈，STEP-KTODER旨在改进现有的方法，如直接偏好优化（DPO）和仅结果的KTO。在HumanEval(+)和MBPP(+)等基准上的评估证明了STEP-KTODER的有效性，并强调了基于执行的标签相对于会降低性能的LLM-as-a-judge注释的关键作用。 AI

影响这项研究通过改进AI代码生成模型从中间执行反馈中学习的方式，可能带来更强大、更准确的AI代码生成模型。

排序理由关于代码生成优化新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 46 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于代码生成优化新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Idris Nechnech, Sehwan Kim, Jimin Seo, Yeongoon Kim, Minhae Oh, Sangwoo Hong, Jungwoo Lee · 2026-08-26 04:00

代码偏好优化的函数级执行反馈

arXiv:2608.23632v1 Announce Type: new Abstract: Process supervision has improved mathematical reasoning, where intermediate steps are naturally expressed as chains of thought. In code generation, however, process supervision remains underexplored because there is no standard noti…

本文如何被排名

报道来源 [1]

代码偏好优化的函数级执行反馈

相关实体

相关话题