My work studies how large language models reason, act, refuse unsafe requests, and portray psychological traits. I turn these questions into benchmarks, open-source systems, and training techniques for more reliable AI applications.
General Agents
Multimodal, tool-using, and collaborative agents for complex, long-horizon tasks.
Abstracts interaction data into atomic decision experiences via hindsight reasoning, then retrieves them at inference through policy-driven wide- and deep-search strategies, improving fine-grained visual perception and multimodal reasoning over trajectory-level retrieval baselines.
Represents reusable multimodal procedures as compact, state-conditioned skill packages — a textual procedure paired with runtime state cards and multi-view keyframes — generated from public trajectories and consulted by a branch-loaded skill agent at runtime.
LLM Reasoning
Mathematical, reflective, and efficient long-chain reasoning.
Tackles overthinking in large reasoning models with a small reflection model that enables parallel sampling and sequential revision during online RL, plus a reflection reward that preserves reflection ability — reducing inference cost by ~35% without sacrificing accuracy.
A dual-reward RL framework that classifies problems as Simple or Hard in real time and adaptively shortens or extends Chain-of-Thought, improving both accuracy and token efficiency on challenging math benchmarks.
LLM Safety
Risk awareness, jailbreak robustness, multilingual safety, and refusal behavior.
LLM Personality
Emotion, personality, and psychological portrayals in conversational AI.
For the chronological list of all papers, see Publications or my Google Scholar page.