Google's RRSI: From Paper to Open-Source Recursive Self-Improvement

Episode 1 · Google Proposes RRSI: Regularizing Recursive Self-Improvement of Agent Harnesses (2026-09-22, 8 posts)

Google Research (Han Rujun, Huaxiu Yao, et al., arXiv:2609.24972, submitted 2026-09-21) published "RRSI: Regularized Recursive Self-Improvement of Agent Harnesses," studying how to apply regularization to the recursive self-improvement of agent harnesses (prompts, control flow, tools, memory and context management), with code and project page open-sourced. Conclusion: regularized RSI still yields gains on out-of-distribution tasks, mitigating self-improvement overfitting.

Confirmed

• Motivation: LLM agent capability is largely amplified by the harness, and recent methods achieve system-level recursive self-improvement (RSI) by iteratively proposing and selecting component-level edits
• The team argues that current "self-improvement" methods—letting agents rewrite their own prompts, tools, memory and workflows—mainly score higher on practiced tasks, with gains often vanishing on new tasks, i.e., overfitting
• Elias (omarsar0) relayed the paper's warning: automated harness optimization inflates benchmark scores while real-task performance degrades
• RRSI introduces regularization into the recursive self-improvement process to constrain the direction of improvement
• Results: 4.7-point gain on OOD tasks and about 30% token savings
• Kangwook Lee noted the contrast with weight-space regularization (e.g., L2), which relies on smoothness/simplicity assumptions about functions, whereas RSI calls for harness-level regularization

Why it matters

• RSI is reshaping how AI agents evolve, but improvements limited to overfitting trained tasks restrict generalization; RRSI offers a simple, effective regularization scheme and a reference path toward generalizable, self-evolving agent harnesses

• Google's RRSI regularizes recursive self-improvement of agent harnesses, +4.7 OOD points — google · 2026-09-22
• RRSI: regularized agent self-improvement gains 4.7 points with 30% fewer tokens — HuaxiuYaoML · 2026-09-22
• Google paper proposes RRSI: regularized recursive self-improvement of agent harnesses — _akhaliq · 2026-09-23
• Paper: RRSI — adding regularization to recursive self-improvement of agents — HuaxiuYaoML · 2026-09-23
• Your Self-Improving Agent Is Probably Overfitting, Researchers Warn — HuaxiuYaoML · 2026-09-23
• Google's RRSI Paper Adds Regularization to Stop Agent Self-Improvement Overfitting — cihangxie · 2026-09-23
• RRSI: Simple Text-Space Regularizers Boost Robustness of Recursive Self-Improving Agent Harnesses — Kangwook_Lee · 2026-09-23
• Google paper: auto-optimized agent harnesses overfit evals — RRSI fixes it — omarsar0 · 2026-09-24

Episode 2 · Google Open-Sources RRSI for Recursive Agent Self-Improvement (2026-09-28, 2 posts)

Google Research open-sourced RRSI, a method that lets agents recursively improve their own framework with frozen model parameters, raising Terminal-Bench to 80.2% and out-of-distribution benchmarks by up to 4.7 points.

• RRSI: Regularizing Recursive Self-Improvement Boosts OOD Agent Benchmarks Up to 4.7 Points — burny_tech · 2026-09-28
• Google open-sources RRSI: agents self-improve their harness, lifting Terminal-Bench 2.1 to 80.2% — sudoraohacker · 2026-09-29