HarnessPro recursively evolves agent harnesses with Pareto cost-performance tuning
The paper introduces HarnessPro, a label-free method that evolves AI agent harnesses through recursive self-improvement, aiming to improve task performance while reducing execution cost. Candidate harnesses are evaluated using LLM-generated tests without access to ground-truth solutions or official tests; specialized agents diagnose execution trajectories, plan updates with different performance-cost priorities and implement them, and normalized weighted squared-distance selection yields cost-focused (lite), balanced (medium) and performance-focused (heavy) harnesses. The authors report that on Terminal-Bench 2, SWE-Bench Pro and ProgramBench, HarnessPro's heavy mode with GPT-5.5 and Codex achieved an average pass-rate gain of 2.0 percentage points and a 26.1% average per-task cost reduction relative to RHO, and say the advantage holds with GLM-5.2 and Claude Code; code is available and the 41-page paper is under review.
The work targets a trade-off that prior recursive self-improvement approaches reportedly leave unresolved: performance gains that come with higher execution costs.
Computer Science > Machine Learning
arXiv:2610.26770 (cs)
[Submitted on 19 Oct 2026]
Title:HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs
Authors:Zhuoshi Pan, ZhiYuan Feng, Yukuo Cen, Honglin Lin, Junru Lu, Zhongxia Chen, Shuo Yang, H. Vicky Zhao, Jie Tang
View a PDF of the paper titled HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs, by Zhuoshi Pan and 8 other authors
#HarnessPro#arXiv#GPT-5.5#Codex#GLM-5.2#Claude Code#Terminal-Bench 2#SWE-Bench Pro#ProgramBench#RHO