Lang Feng

PhD Student @ NTU Singapore

Reinforcement Learning
Large Language Models
Agentic RL

lang005@e.ntu.edu.sg

Google Scholar | Github | Twitter

About Me

I am a second-year Ph.D. student at the College of Computing and Data Science at Nanyang Technological University, fortunate to be advised by Prof. Bo An. Previously, I received my M.Eng. from Zhejiang University under the supervision of Prof. Gang Pan, and my B.Eng. (Hons.) from Southeast University under the supervision of Prof. Liang Wu.

I currently lead the verl-agent project, an open-source framework for training LLM/VLM agents through reinforcement learning. Our team is actively developing reinforcement learning post-training frameworks for multi-agent LLM systems. In addition, I collaborate with Dr. Ming Yan at Alibaba's Tongyi Lab, focusing on mobile agent LLMs.

Research Interests:

Agentic Reinforcement Learning: Training general agents via fundamental RL optimization
LLM Post-training: Enhancing large language models through efficient post-training methods
LLM-based Agents: Developing AI agents powered by large language models

News

2026.01: AgentOCR released! A framework that compresses agent history into visual tokens.
2025.11: One paper accepted by AAAI 2026 (Oral)!
2025.09: GiGPO accepted at NeurIPS 2025! Check out our project!
2025.07: Our verl-agent project talks at Agent for SWE meetup by LF AI & Data Singapore on 7/11.
2025.05: CoSo accepted by ICML 2025! An entropy-based agentic RL algorithm for VLM agent training. Check out our project!
2025.05: ASOR accepted by ICML 2025 (Spotlight)!
2025.05: One paper accepted by KDD 2025!
2024.05: Trajectory Aggregation Tree accepted by ICML 2024 (Spotlight)! Resisting stochastic risk in diffusion planners. Check out our project!

Selected Publications

For a complete list of publications, please refer to my Google Scholar.

* Equal contribution

AgentOCR: Reimagining Agent History via Optical Self-Compression

Lang Feng*, Fuchao Yang*, Feng Chen, Xin Cheng, Haiyang Xu, Zhenglin Wan, Ming Yan, Bo An

Preprint

From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning

Yichao Feng, Haoran Luo, Lang Feng, Shuai Zhao, Anh Tuan Luu

AAAI 2026 Oral

Group-in-Group Policy Optimization for LLM Agent Training

Lang Feng, Zhenghai Xue, Tingcong Liu, Bo An

NeurIPS 2025

GitHub Repo stars

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning

Junru Zhang*, Lang Feng*, Xu Guo, Yuhan Wu, Yabo Dong, Duanqing Xu

BERT2S@NeurIPS 2025

GitHub Repo stars

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

Lang Feng, Weihao Tan, Zhiyi Lyu, Longtao Zheng, Haiyang Xu, Ming Yan, Fei Huang, Bo An

ICML 2025

GitHub Repo stars

Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning

Zhenghai Xue, Lang Feng, Jiacheng Xu, Kang Kang, Xiang Wen, Bo An, Shuicheng Yan

ICML 2025 Spotlight

Diffusion-Guided Diversity for Single Domain Generalization in Time Series Classification

Junru Zhang, Lang Feng, Xu Guo, Han Yu, Yabo Dong, Duanqing Xu

KDD 2025

Resisting Stochastic Risk in Diffusion Planners with the Trajectory Aggregation Tree

Lang Feng, Pengjie Gu, Bo An, Gang Pan

ICML 2024 Spotlight

GitHub Repo stars

Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition

Junru Zhang, Lang Feng, Zhidan Liu, Yuhan Wu, Yang He, Yabo Dong, Duanqing Xu

KDD 2024

Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks

Lang Feng, Qianhui Liu, Huajin Tang, De Ma, Gang Pan

IJCAI 2022

GitHub Repo stars

Honors & Awards

2024 — Outstanding Graduate, Zhejiang University
2022 & 2023 — Award of Honor for Graduate, Zhejiang University
2021 — Outstanding Undergraduate Student, Southeast University

Academic Services

Program Committee/reviewer: ICML (2024-2026), NeurIPS (2025), ICLR (2026), KDD (2025), AAAI (2026)
Journal reviewer: TNNLS