About Jing-Cheng Pang (庞竟成):

I am a fourth-year Ph.D. student at Nanjing University, advised by Professor Yang Yu. In June 2019, I obtained B.Sc. degree from UESTC. In September 2019, I joined the LAMDA group led by Professor Zhi-Hua Zhou, as a Master’s student, excused from the entrance examination. Since September 2021, I was fortunate to be accepted into the Successive Postgraduate and Doctoral program, starting my current Ph.D. studies. Since July 2024, I have been engaged as a visiting student with Prof. Masashi Sugiyama’s team at RIKEN-AIP, Tokyo, Japan.

My research focuses on connecting human and intelligent agent (RL-based or LLM-based) through natural language instructions (effective instruction parsing). Particularly, my study includes:

• Reinforcement Learning: language conditioned RL, optimization algorithm, imitation learning, applications;
• Large Language Models: training, inference-time optimization, agent;
• Embodied Robot: home-service robot, sim2real.

Free free to contact/follow me if you are interested in my work.

Projects

• Awesome-Papers-Autonomous-Agent  
  A collection of recent papers on building autonomous agent. Two topics included: RL-based / LLM-based agents.

Recent News

• 2025.01: Invited talk at HUAWEI NAIE Group. Topic: RL-driven LLM Optimization and Recent Progress [slides].
• 2024.12: InCLET is accepted by AAMAS 2025 as a full paper. We will give an oral presentation at Detriot!
• 2024.09: Our work, KALM, is accepted by NeurIPS 2024!
• 2024.07: I start my visiting to Prof. Masashi Sugiyama’s team at RIKEN-AIP, Tokyo, Japan, doing RL research
• 2024.01: RLC for LLM self-improvement is accepted by ICLR 2024
• 2023.11: Awarded as Top Reviewer (8%) of NeurIPS 2023
• 2023.09: TALAR, for instruction-following agents, gets accepted by NeurIPS 2023
• 2023.09: MG, a new paradigm for environment modelling, gets accepted by Frontiers of Computer Science (FCS, CCF-B)
• 2023.06: O3F for complex robotics manipulation gets accepted by IROS 2023