Lirui Luo

I am a Ph.D. student in the School of Intelligence at Peking University (PKU), majoring in Computer Science and Technology (Intelligent Science and Technology), advised by Cong Fang. I received my B.E. in Communication Engineering from the School of Electronic and Information Engineering at Beijing Jiaotong University (BJTU) in 2023.

I am currently an intern at JD.com’s Tech Genius Team (TGT, Top Young Technical Talent Program), working on Agentic RL post-training that teaches e-commerce coding agents to maintain and use memory while completing long-horizon tasks.

My research interests lie in building general-purpose coding agents that can complete long-horizon tasks and continually improve by learning from rewards obtained through interaction with long-horizon task environments. More specifically, I am interested in (1) agentic reinforcement learning for long-horizon tasks; (2) developing agents’ memory capabilities through RL post-training; (3) agentic RL post-training for recursive self-improvement (RSI) and autoresearch agents; and (4) continual reinforcement learning over unbounded streams of tasks.