Tsinghua

Asif Waliuddin, an engineer, rolled back his fleet of chief-of-staff agents to an older model version after finding the newer model performed worse in real sessions, despite better benchmark scores. C…

Researchers from NUS, Tencent Youtu Lab, and Tsinghua introduced MACT, a multi-agent collaboration framework for visual document understanding that decomposes the task into four specialized agents—pla…

A controlled experiment by Stanford and Tsinghua researchers found that the same AI model can perform up to 6x better depending solely on the harness architecture—the system managing tool calls, conte…