UC Berkeley

Trends

• Open-weight models diversify in architecture, modality, and size

Items

1. Jun 8

   Harness-1 open search agent beats GPT-5.4

   A 20B open-source search agent from UIUC, UC Berkeley, and Chroma, built on gpt-oss-20B, redesigns complex retrieval to reach 73% average recall versus GPT-5.4's 70.9%, with weights and environment released under Apache 2.0.

2. Apr 15

   Value Gradient Flow recasts behavior-regularized RL

   UC Berkeley and UT Austin treat the optimization behind RLHF and offline RL as optimal transport solved by discrete gradient flow from the reference distribution, dropping explicit policy parameterization and beating PPO and DPO variants on D4RL, OGBench, and LLM RL tasks.