HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs
Paper recorded by Signals 4 on 2026-10-19 in cs.LG. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-19 on arXiv · recorded by Signals 4 on 2026-10-20
Category: cs.LG · 机器学习 · first seen 2026-10-20
Abstract
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 task performance while reducing execution cost. In this setting, candidate harnesses are evaluated usin
Read on arXiv →
Cite this page: HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs: the #246 most recent of 749 cs.LG papers we have recorded (as of 2026-10-19). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/harnesspro-recursive-harness-self-improvement-with-pareto-optimization-for-perfo.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free