RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Ranking
Overall
84
Content
90
Popularity
70
Observed public metrics from 1 member.
Merged summary
TL;DR - RRSI regularizes recursive self-improvement of LLM agent harnesses to reduce benchmark overfitting and promote reusable improvements. Across eight coding, workspace, and engineering-design benchmarks, it improved both in-distribution and out-of-distribution performance while using fewer policy tokens.
- Constrains candidate proposals with an annealed edit budget and encourages exploration of previously unused evolution paths.
- Uses a critic to reject benchmark-specific proposals and a pruner to remove changes that are marginal, costly, or obsolete.
- Achieved gains of up to 14.1 points on the evolution split and up to 4.7 points across five out-of-distribution benchmarks.
- Produced a harness using 30% fewer policy tokens than unregularized evolution.
Sources (1)
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Public signals
Hugging Face upvotes 202
TL;DR - RRSI regularizes recursive self-improvement of LLM agent harnesses to reduce benchmark overfitting and promote reusable improvements. Across eight coding, workspace, and engineering-design benchmarks, it improved both in-distribution and out-of-distribution performance while using fewer policy tokens.
- Constrains candidate proposals with an annealed edit budget and encourages exploration of previously unused evolution paths.
- Uses a critic to reject benchmark-specific proposals and a pruner to remove changes that are marginal, costly, or obsolete.
- Achieved gains of up to 14.1 points on the evolution split and up to 4.7 points across five out-of-distribution benchmarks.
- Produced a harness using 30% fewer policy tokens than unregularized evolution.