Cong Chen

The paper argues that the standard Attack Success Rate (ASR) metric for LLM jailbreaks is unstable and systematically inflated, proposing new frameworks to account for stochasticity in both evaluation and generation.

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent performance.

The paper introduces StreamMA, a streaming multi-agent reasoning system that significantly reduces latency and improves effectiveness by passing reasoning steps to downstream agents as they are generated, rather than waiting for the entire chain to complete.