Sign InOpen Brain
arXivPaperNeeds Review

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

RRSI regularizes automated harness editing to curb benchmark overfitting, improving held-out tasks while using fewer policy tokens than unregularized evolution.

arXiv · Sep 21, 2026
Open Source Open MarkdownOpen JSON
Source Summary

RRSI constrains recursive harness editing with an annealed proposal budget, exploration history, a critic and a pruner. Across **eight benchmarks**, it reports gains up to **14.1 points** on the evolution split and **4.7 points** on five out-of-distribution benchmarks.

Practical Implication

When optimizing an agent harness, evaluate reusable mechanisms on held-out tasks and penalize bundled, costly or negligible edits. The reported harness also used **30% fewer policy tokens** than unregularized evolution, making efficiency part of selection rather than an afterthought.

Agent-Ready Context
RRSI constrains recursive harness editing with an annealed proposal budget, exploration history, a critic and a pruner. Across **eight benchmarks**, it reports gains up to **14.1 points** on the evolution split and **4.7 points** on five out-of-distribution benchmarks.

When optimizing an agent harness, evaluate reusable mechanisms on held-out tasks and penalize bundled, costly or negligible edits. The reported harness also used **30% fewer policy tokens** than unregularized evolution, making efficiency part of selection rather than an afterthought.

The gains are maxima rather than aggregate results, and in-distribution improvement remains much larger than the held-out gain. Performance across the individual coding, workspace and design benchmarks is not provided in the supplied material.
Connected Context · Feed7 Judgment

This supplies measured evidence that self-editing harnesses benefit from explicit controls on proposal volume, reuse and cost, rather than unconstrained evolution. Held-out gains support selecting reusable mechanisms, while the much smaller out-of-distribution improvement cautions that benchmark optimization still transfers only partially and does not establish maintainability in production code.

Guide, Verify, Solve — Anirban Chatterjee, SonarRRSI implements the candidate’s guide-and-verify loop at harness-evolution time by using a critic, pruning and benchmark checks to constrain successive edits.From Agent Traces to Agent Simulations — Rustem Feyzkhanov, Snorkel AIReplayable production-derived environments would provide stronger held-out conditions for deciding whether RRSI’s evolved mechanisms generalize beyond its benchmark suite.CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?CordisBench identifies lifecycle interactions as a distinct harness failure mode, making it a relevant kind of held-out test for reusable mechanisms produced by recursive harness editing.Mousepower: agents that can’t be measured, can’t be managed. — Maximillian Piras, YutoriRRSI’s token reduction reinforces the candidate’s view that agent improvement should be selected on outcome and cost together, rather than benchmark gain alone.
Context Map
agentcoding#harness-engineering#agent-evals#agent-reliability
Uncertainty
The gains are maxima rather than aggregate results, and in-distribution improvement remains much larger than the held-out gain. Performance across the individual coding, workspace and design benchmarks is not provided in the supplied material.