English(EN) SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale

新的SE-GoS框架增强了LLM代理的技能检索能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了SE-GoS，一个旨在通过改进技能检索来提高大型语言模型（LLM）代理效率的新颖框架。这种无需训练的方法利用历史执行轨迹演化现有的技能图谱，优化拓扑结构、边权重和技能描述。在SkillsBench上针对三种不同的LLM进行的实验表明，与静态技能加载相比，SE-GoS在任务奖励方面持续提升，并减少了令牌使用量，且改进能有效迁移到新任务。 AI

影响通过优化技能检索来提高LLM代理的效率，有可能降低计算成本并增强复杂任务的性能。

排序理由详细介绍LLM代理新框架的学术论文。[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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM代理新框架的学术论文。[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, infra; 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) · Dawei Fu, Cheng Jiang, Sitian Qian, Huainan Wang, Zhongkai Hao · 2026-09-10 04:00

SE-GoS：可扩展技能库的自演化技能图谱

arXiv:2609.08228v1 Announce Type: new Abstract: Modern LLM agents increasingly rely on reusable skills, yet as skill libraries scale to thousands of entries, effective retrieval becomes a bottleneck. Graph-of-Skills (GoS) addresses this challenge by exploiting dependency-aware gr…

本文如何被排名

报道来源 [1]

SE-GoS：可扩展技能库的自演化技能图谱

相关实体

相关话题