Harness-1用强化学习解决了检索子智能体的搜索策略优化问题，做信息检索或RAG系统的开发者可以直接用开源代码复现，效果接近闭源最强模型。
UIUC与Chroma联合推出Harness-1，一个20B参数的检索子智能体，通过强化学习在状态搜索框架中训练。该框架维护候选池、重要性标记的精选集、证据图和验证记录，策略决定搜索、筛选、验证和停止时机。在8个基准测试中，Harness-1平均精选召回率达0.730，领先下一名开源子智能体11.4个百分点，仅次于Opus-4.6。模型权重和框架代码已开源。
Meet Harness-1: A 20B Retrieval Subagent Trained With Reinforcement Learning Inside a Stateful Search Harness on gpt-oss-20b
UIUC and Chroma's Harness-1 is a 20B retrieval subagent trained with reinforcement learning inside a stateful search harness. The harness maintains the bookkeeping — candidate pool, importance-tagged curated set, evidence graph, verification records — while the policy decides what to search, curate, verify, and when to stop. It reaches 0.730 average curated recall across eight benchmarks, beating the next open subagent by 11.4 points and trailing only Opus-4.6. Weights and harness code are public. The post Meet Harness-1: A 20B Retrieval Subagent Trained With Reinforcement Learning Inside a Stateful Search Harness on gpt-oss-20b appeared first on MarkTechPost .