PulseAugur
中
实时 09:16:05

新框架“Skill Dreaming”通过代码库历史演进 LLM 代理技能

研究人员推出了一种名为“Skill Dreaming”的新型框架,旨在增强大型语言模型(LLM)代理在软件工程中的能力。该系统从代码库中 Pull Request(PR)的历史记录中学习,以持续演进和完善可重用技能库。通过分析 PR 如何修改代码、维护测试以及遵守约定,Skill Dreaming 旨在提高新功能实现和软件代码库的持续维护效率。 AI

影响 该框架有望提高 LLM 代理在复杂软件开发任务中的效率和准确性。

排序理由 该项目是一篇学术论文,详细介绍了一种用于 LLM 代理的新框架。[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 →

新框架“Skill Dreaming”通过代码库历史演进 LLM 代理技能

本文如何被排名

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目是一篇学术论文,详细介绍了一种用于 LLM 代理的新框架。[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, product
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]

  1. arXiv cs.AI TIER_1 English(EN) · Xinyuan Song, Hasibul Haque, Jay Somasundaram, Ryan Turner, Bowen Zhu, Liang Zhao ·

    Skill Dreaming:通过拉取请求流演进存储库技能

    arXiv:2610.36188v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evo…