Researchers trained an open source AI search agent, Harness-1, that outperforms GPT-5.4 on recalling relevant information (opens in new tab)

A joint research collaboration between researchers at the University of Illinois at Urbana-Champaign (UIUC), UC Berkeley, and the open source AI-native vector database platform Chroma , a 20-billion parameter open-source search agent built atop that fundamentally redesigns how AI executes complex retrieval tasks. Harness-1 achieves a massive leap in performance, scoring 73% average on its ability to recall relevant information correctly from a curated dataset, outperforming even GPT-5.4 (70.9...