About Jing-Cheng Pang (庞竟成):
[Research Overview] [Recent News] [Selected Publications] [Projects]
I am interested in buiding smarter and more considerate AI assistant on wearable devices through reinforcement learning. Previously, I worked at Huawei through the TopMinds Talent Program, and received my PhD from Nanjing University (LAMDA Group), where I was very fortunate to be supervised by Prof. Yang Yu to conduct reinforcement learning research. Prior to that, I obtained B.E. from UESTC.
Research Overview
Currently, I am exploring how to leverage RL and LLMs to build Personal Assistant that can proactively assist users, remember things and follow instructions. Specifically, my research includes:
- Proactive AI: data synthesis/selection/orchestration for building LLM-based domain agent.
- Post-training: effective training procedure to optimize domain LLM with RL.
- Instruction following: follow users’ query and execute the tasks on wearable devices.
During the PhD phase, my research focused on connecting human and intelligent agent through natural language. By integrating reinforcement learning (RL) and large language models (LLMs), I aimed to develop systems that not only interpret human intent but also act autonomously and learn iteratively in dynamic environments. Particularly:
- Reinforcement Learning: language-conditioned RL, optimization algorithm, imitation learning, generalist agent;
- Large Language Models: model training, inference-time optimization, LLM-based agent;
- Embodied AI: home-service robot, sim2real policy learning.
Free free to contact/follow me if you are interested in my work.
Recent News
- 2025.07: I join Huawei (AI Data Department) as an AI Researcher, focusing on building Domain Agent with RL and LLMs.
- 2025.06: ASRE (for RL optimization) and LaMSeI (for LLM application) are accepted by TNNLS and TMLR, respectively.
- 2025.03: Invited talk at HUAWEI Jiaxian Community (稼先社区). Topic: Exploration on Intelligent Agent System based on RL and LLMs [slides].
- 2025.01: ReViWo for robotics manipulation under viewpoint disturbance, is accepted by ICLR 2025.
- 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(It’s a pity that we can not get the visa)! - 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
Selected Publications
- Jing-Cheng Pang, Liu Sun, Chang Zhou, Xian Tang, Haichuan Ma, Kun Jiang, Jianlong Wang, Kai Zhang, Sijie Wu, Haoran Cai, Chenwei Wu, Xubin Li and Xin Chen. EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning. ICML 2026. [Paper]
- Jing-Cheng Pang, Peng-Yuan Wang, Kaiyuan Li, Xiong-Hui Chen, Jiacheng Xu, Zongzhang Zhang and Yang Yu. Language Model Self-improvement by Reinforcement Learning Contemplation. ICLR 2024. [paper]
- Jing-Cheng Pang, Nan Tang, Kaiyuan Li, Yuting Tang, Xin-Qiang Cai, Zhen-Yu Zhang, Gang Niu, Masashi Sugiyama and Yang Yu. Learning View-invariant World Models for Visual Robotic Manipulation. ICLR 2025. [paper]
- Peng-Yuan Wang, Jing-Cheng Pang, Chen-Yang Wang, Xu-Hui Liu, Tian-Shuo Liu, Si-Hang Yang, Hong Qian and Yang Yu. InCLET: In-context Learning from Language Models can Improve Embodied Instruction-following. AAMAS (Oral) 2025. [Paper]
- Jing-Cheng Pang, Si-Hang Yang, Kaiyuan Li, Jiaji Zhang, Xiong-Hui Chen, Nan Tang and Yang Yu. KALM: Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts. NeurIPS 2024. [paper]
- Jing-Cheng Pang, Xinyu Yang, Si-Hang Yang, Xiong-Hui Chen and Yang Yu. Natural Language Instruction-following with Task-related Language Development and Translation. NeurIPS 2023. [paper]
- Jing-Cheng Pang, Tian Xu, Shengyi Jiang, Yu-Ren Liu and Yang Yu. Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization. TNNLS. [paper]
[Full publication list][Google Scholar]
Projects
- Awesome-Papers-Autonomous-Agent
A collection of recent papers on building autonomous agent. Two topics included: RL-based / LLM-based agents. - ImagineBench
A benchmark for evaluating RL algorithms that train the policies using both real data and imaginary rollouts from LLMs.
