9:00 - 12:20 April 29, 2025, Sydney
ICC Sydney: International Convention & Exhibition Centre Room C2.5
FOREWORD
The AgentSociety Challenge Workshop brings together academic researchers, industry practitioners, and competition participants to explore innovative applications of large language model (LLM) agents in web experiences. Following the successful completion of the AgentSociety Challenge, this workshop will showcase the winning solutions, provide insights into the latest research directions, and foster discussions on the future of LLM agents in online review platforms and recommendation systems.
The workshop will feature presentations from the top-performing teams from both the User Modeling Track and the Recommendation Track. These presentations will highlight novel approaches, technical innovations, and key insights gained through the competition. Additionally, invited speakers from academia and industry will share their perspectives on the broader implications of agent-based systems for the web.
This workshop serves as a unique platform for knowledge exchange, networking, and collaboration among participants interested in advancing the state-of-the-art in LLM agent technologies. Join us to be part of the exciting discussion on how LLM agents are reshaping our interaction with online platforms and opening new avenues for research and innovation.
Contact Information
Email: LLMSociety-Challenge@outlook.com
Challenge Website: Agentsociety Challenge
SCHEDULE
Workshop Schedule
ICC Sydney: International Convention & Exhibition Centre Room C2.5| Time | Session | Speaker |
|---|---|---|
| 9:00 - 9:15 | Opening: A Brief Introduction to AgentSociety Challenge | Prof. Fengli Xu (Tsinghua University) |
| 9:15 - 9:45 | Keynote: LLM Empowered Agent-based Modeling and Simulation for Computational Social Science | Prof. Yong Li (Tsinghua University) |
| 9:45 - 10:00 | Retrieval Augmented Multi-agent Recommender | Pengfei Zhang (University of Electronic Science and Technology of China) |
| 10:00 - 10:15 | Personalized Recommendation Agents with Self-Consistency | Zijing Wu (University of Science and Technology of China) |
| 10:15 - 10:30 | Intelligent Agents with Adaptive Knowledge Fusion for Personalized Recommendation | Chumeng Jiang (Tsinghua University) |
| 10:30 - 11:00 | Coffee Break | |
| 11:00 - 11:10 | Award Ceremony | |
| 11:10 - 11:25 | A Knowledge-Driven LLM Agent Framework for User Modeling | Shengmao Zhu (Institute of Computing Technology, Chinese Academy of Sciences) |
| 11:25 - 11:40 | Collaborative Optimization Approach for Workflow Agents in User Behavior Modeling | Xinyu Zhang (Renmin University of China) |
| 11:40 - 11:55 | USHB: A Unified Framework for Simulating Human Behaviors in Agent Society through User-and-Item Modeling | Renhuo Zhao (Jiangnan University) |
| 11:55 - 12:10 | EvolutionAgent: A Framework for optimizing Multi-Agent Workflows Automatically | Junhui Luo (Southwest Jiaotong University) |
| 12:10 - 12:15 | Closing Speech | Prof. Fengli Xu (Tsinghua University) |
Organizing Committee
Hosting Organization: Tsinghua University, Infinigence AI, the Web Conference
Committee Members: Yuwei Yan (HKUST-gz); Yu Shang, Qingbing Zeng, Yu Li, Keyu Zhao, Zhiheng Zheng, Xuefei Ning (Tsinghua University); Tianji Wu, Shengen Yan (Infinigence AI).
Committee Chair: Fengli Xu, Yu Wang, Yong Li (Tsinghua University)
AgentSociety Challenge Citation
If you use resources from the AgentSociety Challenge, please cite our paper:
@article{yan2025agentsociety,
title={AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms},
author={Yan, Yuwei and Shang, Yu and Zeng, Qingbin and Li, Yu and Zhao, Keyu and Zheng, Zhiheng and Ning, Xuefei and Wu, Tianji and Yan, Shengen and Wang, Yu and others},
journal={arXiv preprint arXiv:2502.18754},
year={2025}
}