RRSI: Regularized self-improvement helps agents generalize

alphaXiv @askalphaxivOriginally posted 2026.09.23

Open original on X

"RRSI: Regularized Recursive Self-Improvement of Agent Harnesses" RRSI makes self-improving AI agents generalize instead of just overfitting their benchmarks. So instead of letting self-improvement chase whatever boosts the benchmark, RRSI constrains the evolution process to favor changes that are actually reusable. Across coding, agentic workspace and engineering tasks, RRSI improves OOD benchmarks while using 30% fewer policy tokens than unregularized evolution. https://t.co/2fCZAddXz4