The Sequence Knowledge - Issue 945: Learning RSI: Agents that Rewrite their Own Scaffolding

TheSequence · 1 week ago · 18 ● 3 sources

A coding agent from Sakana and Jeff Clune’s lab rewrote its own codebase by adding its own scaffolding and tracking results over about eighty iterations. It improved performance from 20% to 50% on SWE-bench and from 14% to 31% on Polyglot. As a result, the agent gained a persistent history of tried steps, and began validating, generating multiple candidates, and ranking fixes before submitting them.