Meet Harness-1: A 20B Retrieval Subagent Trained With Reinforcement Learning Inside a Stateful Search Harness on gpt-oss-20b

Summary

<p>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.</p> <p>The post <a href="https://www.marktechpost.com/2026/06/06/meet-harness-1-a-20b-retrieval-subagent-trained-with-reinforcement-learning-inside-a-stateful-search-harness-on-gpt-oss-20b/">Meet Harness-1: A 20B Retrieval Subagent Trained With Reinforcement Learning Inside a Stateful Search Harness on gpt-oss-20b</a> appeared first on <a href="https://www.marktechpost.com">MarkTechPost</a>.</p>