Recursive Harness Self-Improvement Raises Agent Performance and Cuts Inference Costs
A new method called Recursive Harness Self-Improvement (RHI) iteratively refines prompt-level harness specifications using pairwise feedback over revision history. Tested on 30 synthetic machine learning tasks, RHI substantially increases the performance ceiling of low-reasoning-effort agents, even surpassing the results of maximum-reasoning-effort settings, while reducing inference costs by up to 60%. The improvements are attributed to better task-specific context management and more effective inter-agent information flow, rather than simply longer reasoning traces.
Why it matters: RHI demonstrates a practical, lightweight approach for continually improving agent harnesses, enabling cost-efficient performance gains in model-harness co-evolution.
Full story at: arXiv AI/ML ↗