Feng Chen

I am currently a Ph.D. student at the College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), supervised by Prof. Bo An.

Previously, I obtained my M.Sc. and B.S. degrees from the School of Artificial Intelligence at Nanjing University, where I was advised by Prof. Zong-Zhang Zhang.

My research interests broadly include Reinforcement Learning, Multi-Agent Systems, and Large Language Model Agents. My current work centers on large language model post-training and agent harness design.

Publications

• Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
  ByteDance Seed Team
  Technical Report, 2025
• EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving
  Shihan Dou*, Ming Zhang*, Chenhao Huang, Jiayi Chen, Feng Chen, Shichun Liu, Yan Liu, Chenxiao Liu, Cheng Zhong, Zongzhang Zhang, Tao Gui, Chao Xin, Chengzhi Wei, Lin Yan, Yonghui Wu, Qi Zhang, Xuanjing Huang
  Advances in Neural Information Processing Systems (NeurIPS), 2025
• Learning to Reuse Policies in State Evolvable Environments
  Ziqian Zhang*, Bohan Yang*, Lihe Li, Bian Yuqi, Ruiqi Xue, Feng Chen, Yichen Li, Lei Yuan, Yang Yu
  International Conference on Machine Learning (ICML), 2025
• Learning to Coordinate with Different Teammates via Team Probing
  Hao Ding*, Chengxing Jia*, Zongzhang Zhang*, Cong Guan, Feng Chen, Lei Yuan, Yang Yu,
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2025 (In press)
• Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling
  Shihan Dou*, Jiayi Chen*, Chenhao Huang*, Feng Chen, Chengzhi Wei, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
  Annual Meeting of the Association for Computational Linguistics (ACL), 2025
• Efficient Multi-Agent Cooperation Learning through Teammate Lookahead
  Feng Chen, Xinwei Chen, Rong-Jun Qin, Cong Guan, Lei Yuan, Zongzhang Zhang, Yang Yu
  Transactions on Machine Learning Research (TMLR), 2025
• Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning
  Cong Guan, Feng Chen, Lei Yuan, Zongzhang Zhang, Yang Yu
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2025
• Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay
  Feng Chen, Fuguang Han, Cong Guan, Lei Yuan, Zhilong Zhang, Yang Yu, Zongzhang Zhang
  International Conference on Learning Representations (ICLR) Workshop GenAI4DM, 2024
• Efficient Human-AI Coordination via Preparatory Language-based Convention
  Cong Guan, Lichao Zhang, Chunpeng Fan, Yichen Li, Feng Chen, Lihe Li, Yunjia Tian, Lei Yuan, Yang Yu
  International Conference on Learning Representations (ICLR) Workshop LLM Agents, 2024
• Dynamics Adaptive Safe Reinforcement Learning with a Misspecified Simulator
  Ruiqi Xue, Ziqian Zhang, Lihe Li, Feng Chen, Yichen Li, Yang Yu, Lei Yuan
  European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2024
• Robust Multi-agent Communication via Multi-view Message Certification
  Lei Yuan, Tao Jiang, Lihe Li, Feng Chen, Zongzhang Zhang, Yang Yu
  Science China Information Sciences (SCIS), 2024
• Multi-Agent Policy Transfer via Task Relationship Modeling
  Rongjun Qin*, Feng Chen*, Tonghan Wang*, Lei Yuan, Xiaoran Wu, Yipeng Kang, Zongzhang Zhang, Chongjie Zhang, Yang Yu
  Science China Information Sciences (SCIS), 2024
• Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation
  Lei Yuan*, Feng Chen*, Zongzhang Zhang, Yang Yu
  Frontiers of Computer Science (FCS), 2024
• One by One, Continual Coordinating with Humans via Hyper-Teammate Identification
  Cong Guan, Feng Chen, Ke Xue, Chunpeng Fan, Lichao Zhang, Ziqian Zhang, Pengyao Zhao, Zongzhang Zhang, Chao Qian, Lei Yuan, Yang Yu
  Transactions on Machine Learning Research (TMLR), 2024
• Learning to Coordinate with Anyone
  Lei Yuan, Lihe Li, Ziqian Zhang, Feng Chen, Tianyi Zhang, Cong Guan, Yang Yu, Zhihua Zhou
  International Conference on Distributed Artificial Intelligence (DAI), 2023 (Best Paper Award)
• Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers
  Lei Yuan*, Ziqian Zhang*, Ke Xue, Hao Yin, Feng Chen, Cong Guan, Lihe Li, Chao Qian, Yang Yu
  AAAI Conference on Artificial Intelligence (AAAI), 2023 (Oral Presentation)
• Efficient Multi-agent Communication via Self-supervised Information Aggregation
  Cong Guan*, Feng Chen*, Lei Yuan, Chenghe Wang, Hao Yin, Zongzhang Zhang, Yang Yu
  Advances in Neural Information Processing Systems (NeurIPS), 2022
• Towards Deployment-Efficient and Collision-Free Multi-Agent Path Finding (Student Abstract)
  Feng Chen, Chenghe Wang, Fuxiang Zhang, Hao Ding, Qiaoyong Zhong, Shiliang Pu, Zongzhang Zhang
  AAAI Conference on Artificial Intelligence (AAAI), 2023 (Student Abstract)
• Multi-Agent Concentrative Coordination with Decentralized Task Representation
  Lei Yuan*, Chenghe Wang*, Jianhao Wang, Fuxiang Zhang, Feng Chen, Cong Guan, Zongzhang Zhang, Yang Yu, Chongjie Zhang
  International Joint Conference on Artificial Intelligence (IJCAI), 2022

Internship Experience

• Research Intern, Agent Harness, Apodex
  Mar 2026 - Present
  Building the agent harness behind Apodex's self-evolving heavy-duty solver — the orchestration and verification layer that coordinates large teams of sub-agents across long-horizon research and problem-solving tasks.
• Large Language Model Research Intern, ByteDance (Seed)
  Sep 2024 - Jun 2025
  Focused on algorithmic research and exploration during the post-training stage of Large Language Models — reinforcement learning for reasoning, optimization, and alignment — and contributed to the Seed1.5-Thinking reasoning model.
• Reinforcement Learning Research Intern, Polixir
  Jul 2022 - Mar 2023
  Built an adversarial reinforcement learning framework enabling two agents to co-train against each other in adversarial environments.
• Reinforcement Learning Research Intern, ByteDance
  Jul 2021 - Oct 2021
  Conducted research within Game AI scenarios, specifically focusing on the training methodologies for intelligent agents and the exploration of algorithms for automated game scene generation.

Academic Service

• Co-organizer, ICLR 2026 Workshop on Multi-Agent Learning and Its Opportunities in the Era of Generative AI
• Invited Speaker, Workshop on Multi-Agent Reinforcement Learning, DAI 2024
• Reviewer, AAAI, NeurIPS, ICLR, ICML, TMLR

Honors & Awards

• National Scholarship, China (2020)
• Outstanding Graduate of Nanjing University (2022)
• Provincial Merit Student, Jiangsu Province (2020)
• Outstanding Student of Nanjing University (2019)