English(EN) Self-Evolving Skills via Surrogate-Guided Solve-and-Reproduce

新框架 reSolve 增强了智能体技能演进和可复现性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

研究人员开发了 reSolve，一个旨在改进智能体技能创建和可复现性的新框架。该系统解决了自我演进技能表现不如人类精心策划的技能以及智能体在部署时难以复现已学技能的常见问题。reSolve 利用代理验证器来增强稀疏奖励信号，并采用由该验证器引导的束搜索来构建解决方案。在测试中，这种方法使一个基础模型能够自我演进出达到 74.9% 的 mean-of-3 分数的技能，显著优于人类精心策划的基线模型和强大的 GPT-5.5/OpenHands 模型。 AI

影响这项研究通过改进智能体技能的开发和执行方式，有望带来更强大、更可靠的 AI 智能体。

排序理由该集群包含一篇详细介绍智能体技能演进新框架的研究论文。[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: 23 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍智能体技能演进新框架的研究论文。[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: 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) · Jiale Liu, Pinze Ren, Yuqi Xia, Huan Wang, Zhenlin Zhao, Siming Dong · 2026-09-01 04:00

通过代理引导的求解与复现实现自我演化技能

arXiv:2608.28638v1 Announce Type: new Abstract: Agent skills are portable packages of instructions and resources an agent consults at deployment. Self-evolving them fails in two ways today. First, skills evolved from scratch underperform human-curated ones and, on a weak model, u…

本文如何被排名

报道来源 [1]

通过代理引导的求解与复现实现自我演化技能

相关实体

相关话题