Patrick Jiang's Harness-1 externalizes memory for a 20B search agent

Patrick Jiang (@patpcj) released Harness-1, a 20 billion parameter search agent that externalizes search state from the model into a structured harness, as detailed in a 13-post thread on X and an accompanying paper. Researchers from the University of Illinois at Urbana-Champaign, UC Berkeley, and Chroma trained the retrieval subagent using reinforcement learning within a stateful search harness. The project argues that search agents underperform because they lack this externalized memory structure.

Patrick Jiang @patpcj introduced Harness 1, a 20B parameter search agent that moves search state outside the model and into a structured harness, according to a 13 post thread on X and the accompanying paper. The paper lists authors from the University of Illinois at Urbana Champaign, UC Berkeley and Chroma, and describes Harness 1 as a retrieval subagent trained with reinforcement learning inside a stateful search harness. The core claim is that search agents fail partly because they are a...