Wei Fu
fuwth17 AT gmail DOT com
I’m currently a fifth-year PhD student in computer science at IIIS, Tsinghua University (expected graduation: June 2026). I am very fortunate to be advised by Professor Yi Wu. Prior to my PhD studies, I received my BEng degree from the Department of Electrical Engineering in 2021.
My research interests lie at the intersection of reinforcement learning (RL) and distributed systems. Currently, I focus on developing AReaL — the fastest and easiest way to scale up agentic RL training for LLM/VLMs. The project has accumulated 2.5k GitHub stars as of September 2025.
I’d describe myself more as a programmer than a researcher.
I enjoy coding, cooking, listening to pop music, and working out at the gym.
News
| Aug 09, 2025 | Introducing ASearcher — a 32B search agent trained with AReaL that exhibits extreme long-horizon agentic execution capability. It achieves SOTA performance compared with other open-source models of the same size. Check out our open-sourced code, dataset, and checkpoints! |
|---|---|
| Aug 01, 2025 | We refactored the legacy AReaL code into AReaL-lite, a light-weight and algorithm-first codebase that prioritizes better development experiences for AI researchers. Check out the quickstart guide to begin your journey with AReaL-lite! |
| Jun 23, 2024 | Introducing ReaLHF, a highly efficient system for RLHF training of LLMs. It can achieve up to 10x higher training speedup than existing open-source systems! Check our open-sourced code and the documentation to get started with ReaL quickly! 🚀 |
