Google open-sources RRSI, a framework that auto-evolves LLM agent harnesses
rohanpaul_ai · x · 2026-10-01
Google Research released RRSI (Regularized Recursive Self-Improvement of Agent Harnesses), an open-source framework plus paper that automatically evolves an LLM agent's harness — prompts, control flow, tools, memory and context management — around a frozen model.
Evolving a harness against a fixed evolve set overfits: in-distribution gains shrink or vanish out of distribution. RRSI keeps the edit space open and regularizes the search trajectory:
- Proposal side: an annealed budget caps bundled edits per candidate; the proposer is conditioned on full edit history so falsified hypotheses aren't redrawn; stalled runs are redirected toward unexercised components.
- Selection side: a critic screens candidates for suite-specific logic before evaluation, with noise-adaptive selection.
The repo is on GitHub with 1.1k stars.
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16