Understand this story
Alex Krentsel, a senior researcher at Google Research and a PhD student at UC Berkeley, shared the self-improving AI agent architecture Exo at Arena. The architecture draws on the exokernel approach from operating systems, splitting the agent into a protected mechanism layer (state, history, keys, and a "guardian") and a fully evolvable policy layer. On benchmarks and open-world RuneScape tasks, Exo is 31-62% cheaper than Codex and Pi. Currently, this presentation has only one report from Arena, with no follow-up developments yet.
AI-generated from public reports
Latest development · Report
Exo Architecture: AI Agent Runtime Self-ImprovementDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 30
Arena
Exo Architecture: AI Agent Runtime Self-Improvement
Alex Krentsel, a Senior Research Scientist at Google Research and a PhD student at UC Berkeley, shared the self-improving AI agent architecture Exo at Arena. Drawing on the exokernel approach from operating systems, it splits the agent into a protected mechanism layer (state, history, keys, and a "guardian") and a fully evolvable policy layer. On benchmarks and open-world RuneScape tasks, Exo is 31-62% cheaper than Codex and Pi.