I build executable environments where agents work inside persistent virtual organizations: they assume roles, use real tools, coordinate under permissions, and act across long-running events. My goal is to close the loop between agent evaluation, trajectory and data synthesis, and RL-based post-training.
Executable agent environmentsOrganizations · Tools · Evals · Data · RLAgentic multimodal understandingLong documents · Long videosPerception-reasoning alignmentModel merging · Cross-modal transfer
News
[Dec. 2025 - Present] Research intern at Microsoft Research Asia (MSRA), working on executable multi-agent environments for realistic office workflows, Agentic Document Understanding, agent evaluation, and data synthesis.