Lijun Li

The paper introduces a unified framework to fairly evaluate LLM agentic capabilities by standardizing diverse benchmarks and separating the effects of the LLM model from the surrounding framework and environment.

The paper introduces AgentSchool, an advanced LLM-powered multi-agent simulator that models learning as state transitions to provide a robust, ethically viable testbed for educational research and pedagogical reform.

SafeSteer proposes a localized on-policy distillation method that restricts safety alignment to specific safety tokens, thereby achieving strong safety performance with minimal degradation to general capabilities and significantly reducing data requirements.