Harness Self-Evolution for Long-Horizon Terminal Agents
Ruhan Wang, Yucheng Shi‡, Zongxia Li, Junyao Yang, Zhongzhi Li, Yue Yu, Haitao Mi, Dongruo Zhou, Leowei Liang
‡ Internship mentor (marked † in the source paper) · Work conducted during an internship at Tencent
RiseHarness iteratively improves agent harnesses while keeping model weights fixed. Successful and failed trajectories, internal execution traces, and a Harness Handbook guide behavior-level edits that are validated through repeated task evaluation.