Workshop on LLM Agents for Social Simulation

November 14, 2025
Seoul, Korea

The 1st Workshop on LLM Agents for Social Simulation

Social simulation has long played a crucial role in exploring the mechanisms underlying human behavior and societal structures. Traditional social simulation relies on rule-based or statistical models, which makes it difficult to capture the complexity and variability of the real world. With the emergence and rapid development of large language model (LLM), new frontiers have been opened toward leveraging LLMs as agent to model human behavior and interactions. This cutting-edge direction has gained significant attention and demonstrated promising results, not only advancing research across a wide range of social science disciplines, but also enabling practical applications in role-playing scenarios. However, this field still faces multiple challenges, such as capturing real-world social phenomena, eliminating bias or ethical considerations, and ensuring usability and reliability. This workshop on LLM Agent for Social Simulation aims to bring together researchers and practitioners from diverse backgrounds to foster interdisciplinary collaboration, address key challenges, explore cutting-edge technologies, and chart promising future directions in this rapidly evolving field.

Important Dates

Submission Open

25 July, 2025

Submission Deadline

15 September, 2025

Paper Acceptance Notification

30 September, 2025

Camera-Ready Submission

01 November, 2025

Organizers

• Yige Yuan — State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences (Homepage)
• Junkai Zhou — State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences
• Bingbing Xu — State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences (Homepage)
• Liang Pang — State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences (Homepage)
• Du Su — State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences
• An Zhang — School of Information Science and Technology, University of Science and Technology of China (Homepage)
• Teng Xiao — Allen Institute for AI & University of Washington (Homepage)
• Fengli Xu — Tsinghua University (Homepage)
• Zhaochun Ren — Leiden University (Homepage)
• Xu Chen — Renmin University of China (Homepage)

Keynote Talks

Keynote Talk I

Junming Huang

Princeton University

Research Scientist

Keynote Talk II

Zhongyu Wei

Fudan University

Associate Professor

Accepted Papers

15 papers were submitted; 8 were accepted. Three papers received the LASS Outstanding Paper Award.

1. Simulating Misinformation Propagation in Social Networks using Large Language Models  [Outstanding]
2. Can Large Language Model Agents Simulate Human Trust Behavior?  [Outstanding]
3. Multi-Personality Generation of LLMs at Decoding-time  [Outstanding]
4. GMoE: Empowering LLMs Fine-Tuning via MoE Graph Collaboration
5. DuST: Dual-Stage Tuning of LLMs for Next-Post-Topic Prediction in Social Media Bots
6. Rethinking Implicit Hate Speech Detection: Focusing on Latent Hate Components via Structured Argumentation
7. Beyond Single-expert Recommenders: Collective Intelligence through a Network of Experts
8. MARS: A Multi-Agent Simulation Framework for Rumor Propagation on Social Media