Agents that remember,
reason & improve.
I am an Applied Research Scientist at Alibaba Group. My current work focuses on LLM post-training, agent memory, and reliable long-horizon task execution.
Previously at Huawei, I contributed to MindSpore, MindRLHF, and the MetaERP agent for invoice reconciliation and validation. I received my M.Sc. in Computer Science and Technology from Tianjin University, advised by Prof. Jianye Hao. My earlier research focused on deep reinforcement learning, transfer learning, and multi-task reinforcement learning, with an emphasis on improving sample efficiency, incorporating prior knowledge, and learning shared representations across tasks.
Publications
Experience

Applied Research Scientist · Hangzhou, China
Building LLM agent systems, with a focus on post-training, agent memory, and reliable long-horizon task execution.

Education

M.Sc. in Computer Science & Technology
Advised by Prof. Jianye Hao. Research in deep reinforcement learning, transfer learning, and multi-task reinforcement learning.