# HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs > Source: > Published: 2026-10-20 03:30:02+00:00 Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI), but their performance gains often come with higher execution costs. We introduce HarnessPro, a label-free method for evolving harnesses to improve tas