Lei Bai

Coding agents using the Harness-of-Harness framework can achieve over 52% performance improvement in autonomous software development, revolutionizing how we approach LLM-based coding tasks.

Treating a frozen large language model as the decision-maker in molecular design dramatically enhances candidate selection and optimization efficiency.

Short-context models can achieve superior reasoning performance by leveraging long-context teacher models through innovative token alignment and training strategies.

Structured composition unlocks significantly better agent performance compared to flat skill invocation, even with the same skill set.