A Concise Introduction to LLM-based Multi-agent Systems
AAMAS 2026 Tutorial. Paphos, Cyprus. May 2026.
Academic Portfolio
Yang
Chen
Researcher at Shanghai AI Lab working across reinforcement learning, multi-agent systems, game theory, and LLM-based reasoning.
Profile
Bio
I obtained my PhD in computer science from the University of Auckland, after completing First Class Honours there in 2018. Before moving to New Zealand, I received my B.S. in computer science from Beijing Institute of Technology.
My research spans reinforcement learning, multi-agent systems and game theory. A central thread is learning in large populations, where mean-field perspectives help scale multi-agent reasoning. More recently, I have focused on LLMs, behaviour modelling, ethical AI, and responsible AI.
Outside research and teaching, I spend time hiking and making photographs. That visual sensibility matters to how I present research too: clarity, sequence, atmosphere, and strong composition.
Contact
- Email[email protected]
- LinkedInyang-chen-93a28321a
- ScholarGoogle Scholar profile
- GalleryPersonal online gallery
Project
Agent Panel
The world's first "Research Moltbook x AI Agent Quora" community, centered on one question, many answers, and multi-agent discussion.
Timeline
Experience
Appointments
Jul 2025 - Present
ResearcherShanghai AI Lab
Oct 2024 - Jul 2025
Senior Research AssociateUniversity of New South Wales
Jun 2021 - Sep 2024
Research FellowUniversity of Auckland
Visiting and Industry
Oct 2024
Visiting researcherUniversity of Copenhagen
Sep 2020 - Jan 2021
Research InternAlibaba DAMO Academy
Education
Nov 2018 - Sep 2022
PhD in Computer ScienceUniversity of Auckland
Jul 2017 - Jul 2018
First Class Honours in Computer ScienceUniversity of Auckland
Aug 2013 - Jun 2017
BSc in Computer Science and TechnologyBeijing Institute of Technology
Public Presence
Talks & Teaching
Talks
From One to Infinity: New Perspectives and Methods for Inverse Reinforcement Learning
University of Copenhagen. Denmark. 8 October 2024.
Identify and Mitigate Bias-Perpetuating Behaviours: Decoding Animal Behaviour via Many-agent IRL
AAMAS 2024 Affinity Group Event on Diversity in AI. Auckland. 7 May 2024.
Towards Many-agent Inverse Reinforcement Learning via Mean Field Games
DAI 2023. Singapore. 2 December 2023.
Promotional talk for AAMAS 2024 at the closing session of AAMAS 2023
AAMAS 2023. London. 2 June 2023.
Mean Field Game as a Framework for Many-agent Inverse Reinforcement Learning
ML and MFG seminar. Online. 6 December 2022.
Teaching
COMPSCI 713 Artificial Intelligence Fundamentals
Semester 1, 2024, University of Auckland.
COMPSCI 761 Advanced Topics in Artificial Intelligence
Semester 2, 2022-2023, University of Auckland.
Funding
Grants
AI-based behavioural analytics for live sports broadcast
2024 - 2026 / Associate Investigator / MBIE Endeavour Fund / 1 Million NZD
Recognition
Awards
AAMAS 2022 Scholarship
April 2022
Google Global PhD Fellowship Nomination (Australia & New Zealand)
August 2020
Best Paper Award, BSCI 2019
July 2019
Summer scholarship funding from Precision Driven Health
July 2019
University of Auckland Doctoral Scholarship
November 2018 - November 2021
Community
Academic Service
Conference reviewer
ICML 2026, ICLR 2025-2026, NeurIPS 2025, AAAI 2026, IJCAI 2025, ACL 2024-2025, AAMAS 2023-2025, ECAI 2024-2025, COLM 2025.
Journal reviewer
JMLR.
Event organising
Local Co-chair of AAMAS 2024; Co-chair of the AAMAS 2024 AAAI track.
Archive
Publications
When publisher links are paywalled, the list points to open versions where available. For the most recent preprints, see the CV.
(Reinforcement) Learning in Large Language Models
-
CraftUtopia: A LLM-based Multi-Agent System for Collaborative Construction in Minecraft.
Wanli Fu, Hao Li, Siyue Ren, XingChenxi, Yang Chen, Chu Chen, Zhen Wang, Shuyue Hu.
AAMAS 2026OpenReview
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey.
Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Yue Liao, Hongru Wang, Mengyue Yang, Heng Ji, Michael Littman, Jun Wang, Shuicheng Yan, Philip Torr, Lei Bai.
Transactions on Machine Learning Research 2026arXiv
-
Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiency Scales Test-Time Compute.
Jianhao Chen, Zishuo Xun, Bocheng Zhou, Qiaosheng Zhang, Yang Chen, Wei Hu, Yuzhong Qu, Wanli Ouyang, Shuyue Hu.
AAAI 2026arXiv
Reinforcement Learning, Inverse Reinforcement Learning & Imitation Learning
- Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm. Yang Chen, Menglin Zou, Jiaqi Zhang, Yitan Zhang, Junyi Yang, Gael Gendron, Libo Zhang, Jiamou Liu, Michael Witbrock.
-
Situational-Constrained Sequential Resources Allocation via Reinforcement Learning.
Libo Zhang, Yang Chen, Toru Takisaka, Kaiqi Zhao, Weidong Li, Jiamou Liu.
IJCAI 2025arXiv
-
Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas.
Hao Guo, Chunjiang Mu, Yang Chen, Chen Shen, Shuyue Hu, Zhen Wang.
Neurocomputing 2024arXiv
- Meta-Inverse Reinforcement Learning for Mean Field Games with Probabilistic Context Variables. Yang Chen, Xiao Lin, Bo Yan, Libo Zhang, Jiamou Liu, Neset Ozkan Tan, Michael Witbrock.
- Density-based Correlated Equilibrium for Markov Games. Libo Zhang (equal contribution), Yang Chen (contact, equal contribution), Toru Takisaka, Bakh Khoussainov, Michael Witbrock, Jiamou Liu.
- Adversarial Inverse Reinforcement Learning for Mean Field Games. Yang Chen, Libo Zhang, Jiamou Liu, Michael Witbrock.
-
Interconnected Neural Linear Contextual Bandits with UCB Exploration.
Yang Chen, Miao Xie, Jiamou Liu, Kaiqi Zhao.
PAKDD 2022Paper
- Individual-Level Inverse Reinforcement Learning for Mean Field Games. Yang Chen, Libo Zhang, Jiamou Liu, Shuyue Hu.
-
Social Capital Games as a Framework for Social Structural Pattern Emergence.
Yang Chen, Jiamou Liu.
ASONAM 2020Paper
- Social Structure Emergence: A Multi-agent Reinforcement Learning Framework for Relationship Building. Yang Chen, Jiamou Liu, He Zhao, Hongyi Su.
Multi-agent Behaviour Modelling and Simulation
- Behaviour Modelling of Social Animals via Causal Structure Discovery and Graph Neural Networks. Gael Gendron (co-first), Yang Chen (co-first), Mitchell Rogers, Yiping Liu, Mihailo Azhar, Shahrokh Heidari, David Arturo Soriano Valdez, Kobe Knowles, Padriac O'Leary, Simon Eyre, Michael Witbrock, Gillian Dobbie, Jiamou Liu and Patrice Delmas.
- Meerkat Behaviour Recognition Dataset. Mitchell Rogers, Gael Gendron, David Soriano Valdez, Mihailo Azhar, Yang Chen, Shahrokh Heidari, Caleb Perelini, Padriac O'Leary, Kobe Knowles, Izak Tait, Simon Eyre, Michael Witbrock, Patrice Delmas.
- MSDC: Non-intrusive Load Monitoring with a Dual-CNN Model. Jialing He, Jiamou Liu, Zijian Zhang, Yang Chen, Yiwei Liu, Bakh Khoussainov, Liehuang Zhu.
Natural Language Processing and Reasoning
-
Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning.
Qiming Bao, Gael Gendron, Alex Peng, Wanjun Zhong, Neset Tan, Yang Chen, Michael Witbrock, Jiamou Liu.
ICONIP 2024arXiv
-
Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning.
Qiming Bao, Alex Yuxuan Peng, Zhenyun Deng, Wanjun Zhong, Gael Gendron, Timothy Pistotti, Neset Tan, Nathan Young, Yang Chen, Yonghua Zhu, Paul Denny, Michael Witbrock, Jiamou Liu.
ACL 2024 FindingsarXiv
-
Neuromodulation Gated Transformer.
Kobe Knowles, Joshua Bensemann, Diana Benavides Prado, Vithya Yogarajan, Michael Witbrock, Gillian Dobbie, Yang Chen.
ICLR 2023 Tiny PapersarXiv
-
Multi2Claim: Generating Scientific Claims from Multi-Choice Questions for Scientific Fact-Checking.
Neset Tan, Trung Nguyen, Josh Bensemann, Alex Peng, Qiming Bao, Yang Chen, Mark Gahegan, Michael Witbrock.
EACL 2023Paper
-
Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering.
Zhenyun Deng, Yonghua Zhu, Yang Chen, Michael Witbrock, Patricia Riddle.
IJCAI 2022Paper
- Prompt-based Conservation Learning for Multi-hop Question Answering. Zhenyun Deng, Yonghua Zhu, Yang Chen, Qianqian Qi, Michael Witbrock, Patricia Riddle.
-
Eye Gaze and Self-attention: How Humans and Transformers Attend Words in Sentences.
Joshua Bensemann, Alex Yuxuan Peng, Diana Benavides-Prado, Yang Chen, Neset Ozkan Tan, Paul Michael Corballis, Patricia Riddle, and Michael Witbrock.
CMCL 2022PDF
-
An explainability analysis of a sentiment prediction task using a transformer-based attention filter.
Neset Ozkan Tan, Joshua Bensemann, Diana Benavides-Prado, Yang Chen, Mark Gahegan, Lia Lee, Alex Yuxuan Peng, Patricia Riddle, Michael Witbrock.
Advances in Cognitive Systems 2021Paper
Graph Theory
-
A Graph Transformer against Graph Perturbation by Flexible-pass Filter.
Yonghua Zhu, Jincheng Huang, Yang Chen, Robert Amor, Michael Witbrock.
Information FusionPaper
-
Robust Node Classification on Graph Data with Graph and Label Noise.
Yonghua Zhu, Lei Feng, Zhenyun Deng, Yang Chen, Robert Amor, Michael Witbrock.
AAAI 2024Paper
-
Efficient Size-Prescribed k-Core Search.
Yiping Liu, Bo Yan, Bo Zhao, Hongyi Su, Yang Chen, Michael Witbrock.
ASONAM 2023arXiv
-
Chain of Propagation Prompting for Node Classification.
Yonghua Zhu, Zhenyun Deng, Yang Chen, Robert Amor, Michael Witbrock.
ACM MM 2023Paper
-
A Reinforcement Learning Approach to Gaining Social Capital with Partial Observation.
He Zhao, Hongyi Su, Yang Chen (contact), Jiamou Liu, Hong Zheng, Bo Yan.
PRICAI 2019Paper
- Dynamic Relationship Building: Exploitation Versus Exploration on a Social Network. Bo Yan, Yang Chen, Jiamou Liu.
-
Can Reinforcement Learning Enhance Social Capital?
He Zhao, Hongyi Su, Yang Chen, Jiamou Liu, Bo Yan, Hong Zheng.
WISE 2020 WorkshopPaper
- Distributed Community Detection over Blockchain Networks Based on Structural Entropy. Yang Chen, Jiamou Liu.
- Becoming Gatekeepers Together with Allies: Collaborative Brokerage over Social Networks. Yang Chen, Jiamou Liu.