Zhuoshi Pan, ZhiYuan Feng, Yukuo Cen, Honglin Lin, Junru Lu, Zhongxia Chen, Shuo Yang, H. Vicky Zhao · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26770 · open-access PDF
Harness 开发在构建有能力的 AI 代理方面发挥着至关重要的作用。最近的方法通过反复自我改进 (RSI) 来改进 Harness,但其性能增长往往伴随着更高的执行成本。我们引入 HarnessPro,一种无标签的方法,用于改进 AI 代理来提高任务性能,同时降低执行成本。在这种情况下,候选人 Harness 使用 LLM 生成的测试进行评估,而无需访问实地解决方案或官方测试。
Machine translation (Meta M2M100); the English original follows.
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 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 imple
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26770, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange