cs.LGNov 16, 2026

DeltaHarness: Self-Evolving Harnesses for Resource-Adaptive Tool Execution

Authors: Lecheng Yan, Jianze Lin, Xicheng Han, Xiantao Xu, Wenxi Li, Chenyang Lyu

Organizations: University of Science and Technology of China · Beijing Normal University · Zhejiang University · Dmall Inc. · 

Abstract

Tool-using agents rely on execution harnesses to organize and schedule tool operations. The same task and resource description can conceal runtime conditions that reverse the latency ordering of valid execution plans. Resolving this uncertainty requires firsthand execution in the target setting. We introduce DeltaHarness, an execution-guided policy-search method that adapts agent harnesses from cold-start measurements. Its QHI loop uses the observed response to update runtime dispatch, revise physical plans, and select experiments for later proposals. An independent confirmation panel controls policy replacement. With fixed dispatch, a revised materialization policy reduces complete-delivery latency by 30.0% on one video-editing task across three fresh pairs. On held-out tasks, the evolved policies reduce latency by 8.2% relative to the best fixed plan in one seed and by 4.6% relative to the initial proposal in another.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Harness-Delta Attribution: Dissecting Gains From Harness Evolution

    Oct 15, 2026Wenxuan Ding, Qin Lu, Changlong Yu +5Agent Harness OptimizationAgent Harness Self-Evolution

  2. Turbo Harness: Instance-Adaptive Harness Optimization

    Sep 30, 2026Tunyu Zhang, Hao Wang, Kai Xu +1Agent Harness OptimizationSelf-Improving Agents

  3. Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

    Aug 3, 2026Shuai Shao, Kangning Zhang, Qingyao Li +7Agent Harness OptimizationLLM Agent Self-Improvement