AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
anthropicopenaiagenthuggingface daily papersjake whartonai安全it之家gpusolidot港股

搜索：RRSI

共命中 3 条（服务端检索）
Google 开源 RRSI：让智能体在冻结 LLM 上递归自改进 harness，同时防止基准过拟合
Google 联合多校开源 RRSI 框架，在冻结 LLM 前提下自动进化智能体 harness，并用正则化抑制基准过拟合，8 项基准最高提升 14.1 分。
研究前沿 arXiv · 昨天 阅读 3·访客 3
Google Research Open-Sources RRSI: AI Agents That Improve Their Own Harness Without Overfitting
Google Cloud AI Research**, with UNC-Chapel Hill, Stanford and Washington University in St. Louis, has released RRSI (Re…
智能体 MarkTechPost · 3天前 阅读 6·访客 6
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and co…
智能体 HuggingFace Daily Papers · 9-21 阅读 21·访客 20