Chen Qian

Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

Towards Self-Evolving Agent Benchmarks : Validatable Agent Trajectory via Test-Time Exploration

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models

REEF: Representation Encoding Fingerprints for Large Language Models

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning

DEAN: Deactivating the Coupled Neurons to Mitigate Fairness-Privacy Conflicts in Large Language Models