Ai Agents

Tsinghua and Zhipu's HarnessPro lets agents rewrite their own harness, cutting task cost 26.1%: HarnessPro, from Tsinghua, Zhipu and partners, lets agents study their own runs and rewrite their harness without reference answers. It raised pass rates by 2 points and cut cost per task by 26.1%.

AI Agents • Pandaily

Anthropic study finds experts adopted a coin-flip AI agent's views up to 86% of the time: Anthropic gave 50 experts an AI agent whose preferences were set by coin toss. On judgment calls, experts followed the agent's view up to 86 percent of the time, and most believed the conclusions were their own.

AI Research • The Decoder

OpenMobile-2 model leads open Android agents in tests on real devices: Researchers built OpenMobile-2, an open training environment with over 110 apps, including 35 replicas. On real Android devices, their model scores highest among open agents, the authors say. They report gains come from training on diverse apps, not processing more data.

AI & Mobile • The Decoder