Arena 转发了 Google Research 与 UC Berkeley 等机构的研究成果 Exo，这是一种能在运行时自我改进的 AI 智能体架构。该架构借鉴操作系统的 exokernel 思想，将智能体拆分为受保护的机制层和可进化的策略层，在基准测试和开放世界 RuneScape 任务中相比 Codex 和 Pi 成本降低 31% 到 62%。
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