Researchers from UIUC and Chroma have released Harness-1, a 20B retrieval subagent trained with reinforcement learning inside a stateful search harness. The sys
Researchers from UIUC and Chroma have introduced Harness-1, a 20 billion parameter retrieval subagent. This system utilizes reinforcement learning within a stateful search harness, maintaining internal bookkeeping such as candidate pools and evidence graphs. Harness-1 has demonstrated strong performance, achieving an average curated recall of 0.730 across eight benchmarks, and its weights and code have been made publicly available. AI
IMPACT Provides a new open-source retrieval subagent for AI research and development.