The authors describe Exo, a runtime in which the agent revises its own harness policy (context construction, tools, memory) while it works, using the same code-editing tools it uses for ordinary tasks. A small protected layer keeps…
In the News: November 5, 2026 (Extra 3)
A Berkeley paper has an agent rewrite its own harness mid-task, and Rivet launches an actor runtime as an alternative to per-agent sandboxes.
Extra edition
Machine-readable
Download Markdown
Story
A Berkeley paper has agents rewrite their own harness during the task and reports lower model cost
Read story →
Story
Rivet launches an open-source actor runtime for agents, with vendor benchmarks against sandboxes
Rivet's founders say each agent gets a long-lived actor with in-memory state, durable SQLite storage, and hibernation when idle, instead of its own sandbox. Writes are acknowledged once SSDs in two of three availability zones hold them,…