CV | Zenghuang Fu

Name	Zenghuang Fu
Email	fuzenghuang24@ia.ac.cn

Master’s student at the Institute of Automation, Chinese Academy of Sciences, advised by Weiliang Meng and Xiaopeng Zhang. My research interests are long-horizon credit assignment for agentic reinforcement learning, agentic search, self-evolving agents and AutoResearch, with a background in agentic memory, agentic RL and long-video understanding with multimodal LLMs. I am actively looking for PhD positions.

National First Prize, China Undergraduate Mathematical Contest in Modeling (CUMCM), 2022

Provincial First Prize (Fujian), National Undergraduate Market Survey and Analysis Competition (Zhengda Cup), 2022

∗ denotes equal contribution (co-first author); † denotes corresponding author. Full author lists are on the publications page.

Awesome-Long-Horizon-Credit-Assignment-for-Agentic-RL

A curated reading list of papers, methods and resources on long-horizon credit assignment for agentic RL.
- https://github.com/Zenghuang-Fu/Awesome-Long-Horizon-Credit-Assignment-for-Agentic-RL
DMTrack

Reference implementation of the DMTrack UAV multi-object tracker.
- https://github.com/Zenghuang-Fu/DMTrack

Agentic RL: Long-horizon credit assignment, agentic reinforcement learning

Agents: Agentic search, self-evolving agents, AutoResearch, agentic memory

Multimodal: Long-video understanding with multimodal LLMs, MLLM reasoning

Programming: Python, PyTorch, C++

Chinese: Native speaker

English: Professional working proficiency

CV