English(EN) Let the Fixer Decide: Training a Code Localizer from the Fixer's Likelihood

新的修复者引导定位方法提高了代码代理的效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-09 10:18

研究人员开发了一种名为修复者引导定位（FGL）的新方法，以更有效地训练代码定位器。FGL 不仅关注补丁编辑的文件，还使用固定的修复者模型对建议的定位进行评分，从而在无需测试运行或强化学习的情况下指导训练过程。这种方法在 Kaggle 竞赛中应用于 Gemma 4 E4B，证明 FGL 可以帮助代理用更少的代码和更少的错误找到 bug，从而提高任务完成率和探索效率。 AI

影响这项研究可能带来更高效、更准确的编码助手，特别是对于较小的模型。

排序理由该集群描述了一篇关于训练代码定位器的新颖方法的最新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 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: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇关于训练代码定位器的新颖方法的最新研究论文。[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: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-11-09 10:18

由修复器决定：从修复器似然性训练代码本地化器

Code localizers are usually trained to predict the files a reference patch edits, but the code a fixer needs to read is not the same as the code it changes. We propose Fixer-Guided Localization (FGL): the localizer proposes several localizations, a frozen fixer scores each by how…

本文如何被排名

报道来源 [1]

由修复器决定：从修复器似然性训练代码本地化器

相关实体

相关话题