arXiv · cs.AI · Alexander Krentsel, Sylvia Ratnasamy, Ion Stoica, Martin Casado, Ankur Goyal2026-11-03 13:00 · 10 小时前模型评分49

Exo：一种可在运行中自我改进的智能体运行时架构

Exo: An Architecture for Self-Improving Systems at Runtime

导读

Exo 是一种让人工智能（AI，Artificial Intelligence）智能体（Agent）在执行任务的同时安全学习、自行修改自身策略的运行时架构。

分类置信度

中 · 待人工复核

来源级别：媒体与个人

事件类型：研究发布

证据摘录

“We present Exo, an agent runtime architecture for safe learning during ongoing work that collapses the optimization loop into task execution, allowing agents to revise both their harness and their strategies for further improvement.”

来源：arXiv · cs.AI · arxiv.org