Preprint
Aug 2026
Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories
This work introduces Harness-R1, the first method, to the authors' knowledge, that makes failure-conditioned, lifecycle-wide editing of an existing executable runtime a learned capability, and post-trains a dedicated harness engineer with online reinforcement learning so that its edits are optimized for the realized task success they produce.
Shuai Shao, Kangning Zhang, Qingyao Li et al.
· 6 citations
· ⚡2