Jun Yan

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Cost-effective Agent Test-time Scaling via Budget-Aware Thinking

AlpaGasus: Training a Better Alpaca with Fewer Data

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection

Instruction-following Evaluation through Verbalizer Manipulation