English(EN) Beyond pass@k: Redundancy-Aware RLVR for Multi-Sample Code Generation

新的RLVR方法解决代码生成冗余问题

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-28 04:00

研究人员开发了一种名为冗余感知RLVR的新方法，以改进大型语言模型生成代码的质量。该方法解决了生成代码样本之间过于相似的问题，这会影响性能。通过整合基于代码相似度检测的反冗余奖励，该方法旨在生成更多样化且可执行的代码，其性能通常能与现有技术相媲美或超越。 AI

排序理由该集群包含一篇学术论文，详细介绍了代码生成评估的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了代码生成评估的新方法。[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: 116 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Le Bronnec Florian, Alexandre Verine, Rio Yokota, Benjamin Negrevergne · 2026-05-28 04:00

超越pass@k：面向多样本代码生成的冗余感知RLVR

arXiv:2605.28022v1 Announce Type: new Abstract: LLMs for code generation are commonly evaluated in repeated-sampling settings using Pass@k, where multiple candidate programs are executed against unit tests under a finite sampling budget. While recent verifier-based reinforcement …