Google's RRSI regularizes recursive self-improvement of agent harnesses, +4.7 OOD points
google · hf · 2026-09-22
Google Research introduces RRSI, adding regularization to recursive self-improvement of LLM agent harnesses. RSI tends to overfit training tasks, with in-distribution gains vanishing on OOD benchmarks. RRSI constrains evolution via a proposer with temporally annealed edit budgets and exploration encouragement, plus a selector with a critic and pruner to favor reusable mechanisms over benchmark-specific tweaks. Across eight benchmarks, RRSI gains up to 14.1 points on the evolved split and up to 4.7 on five OOD benchmarks, with 30% fewer policy tokens. Code is open-sourced.
More from coding & agent
- Pigment Agents now reads and posts in Slack, inheriting user permissions — mattturck · 2026-11-12
- Map of the agent economy: 50+ startups across payments, spend control, identity, memory — venturetwins · 2026-11-12
- VentureTwins maps the B2A economy: dozens of agent infra and app companies in first series installment — venturetwins · 2026-11-12
- Google releases 76-page 'Agents Companion' whitepaper on agent engineering — mdancho84 · 2026-11-12
- Spinning up containers for 20-line agent tools is backwards: Safescript compiles provable, 50ms-deploy apps — uriwa · 2026-11-12
- Stripe launches claimable sandboxes: frictionless payment integrations for AI agents — jeff_weinstein · 2026-11-12