Exo：可运行时自我改进的AI智能体架构
What if AI agents could safely improve their own harness at runtime? UC Berkeley PhD candidate and senior researcher @AlexKrentsel from @...
摘要
UC Berkeley 博士生、Google Research 高级研究员 Alex Krentsel 在 Arena 介绍了自改进 AI 智能体架构 Exo，借鉴操作系统的 exokernel 思想，将智能体拆分为受保护的机制层（状态、历史、密钥和"guardian"）与可完全演化的策略层。在基准测试和开放世界 RuneScape 任务上，Exo 比 Codex 和 Pi 便宜 31-62%。
摘要由模型根据原文撰写，以原文为准。
正文 · 原文
What if AI agents could safely improve their own harness at runtime? UC Berkeley PhD candidate and senior researcher @AlexKrentsel from @GoogleResearch recently presented his work on self-improving AI agents at Arena HQ.
This architecture, Exo, borrows the exokernel idea from operating systems, separating an agent into a protected mechanism layer (state, history, secrets, and a "guardian") and a fully evolvable policy layer.
Alex walks through the design, results on benchmarks and open-world RuneScape tasks, where Exo was 31-62% cheaper than Codex and Pi, and more.
Big thanks to @AlexKrentsel for joining us to present his work with @istoica05, @martin_casado, @ankrgyl, Sylvia Ratnasamy, @BerkeleySky, and @netsyslab.
来源：Arena.ai · x.com
引用原文
arena. What if AI agents could safely improve their own harness at runtime? UC Berkeley PhD candidate and senior researcher @AlexKrentsel from @...[EB/OL]. (2026-10-30)[访问日期]. https://x.com/arena/status/2115865351397511204.