Workshop on LLM Agents for Social Simulation

November 14, 2025
Seoul, Korea

Important Dates

Submission Open

25 July, 2025

Submission Deadline

31 August, 2025

Paper Acceptance Notification (highly desirable)

30 September, 2025

Camera-Ready Submission

01 November, 2025

Submission Website

Please submit your papers via OpenReview:
https://openreview.net/group?id=ACM.org/CIKM/2025/Workshop/LASS

Submission Requirements

Authors are invited to submit full-length research papers, including those that have already been published elsewhere. Submissions should be relevant to the workshop theme and meet the standards of top-tier international research conferences.

Manuscripts must be submitted in PDF format. Papers should follow the official ACM sigconf two-column template.

• Full papers: maximum 9 pages (including appendix), plus unlimited pages for references and GenAI usage disclosure.
• Short papers: maximum 4 pages, plus unlimited references and GenAI usage disclosure.
• Any appendix must be included within the 9-page limit (excluding references).
• Submitted papers will undergo double-blind review: all submissions must be properly anonymized. Non-anonymized papers will be desk-rejected without review.
• LLM-generated text is prohibited unless part of the experimental analysis. AI tools may only be used for light editing (e.g., grammar checks).
• Accepted papers will not appear in formal proceedings, so future submission to other venues will not be affected.
• Accepted papers can choose to be fast-tracked to the JCST (CCF-B) journal.
• A Best Paper Award has been established for the symposium.

Call for Papers

• Alignment with Social Value
  • Environment Construction: Text, virtual, embodied, etc.
  • Agent Architecture: Mechanism or module such as memory, perception, preference, reflection, action, etc.
  • Alignment and Personalization: Reinforcement learning from human feedback, offline preference optimization, inference-time alignment, multi-dimensional alignment and role play, etc.
  • Reasoning & Planning: Reinforcement learning from verifiable reward, multi-turn/long-horizon decision-making, etc.
• Validation of Social Phenomenon
  • Micro-level: Individual behaviors including event evolution, interaction patterns, interpersonal dynamics mechanisms, etc.
  • Macro-level: Large-scale patterns including societal trends and emergent group behaviors characterizing social phenomena, etc.
• Evaluation Methodologies
  • Metrics: Metrics for emotion, cognition, preferences, etc.
  • Benchmarks: Testbeds, benchmarks, leaderboard, etc.
• System Scalability
  • Scale: Large populations, high-order interactions, etc.
  • Efficiency: Agent systems designed for parallel processing, distributed computing, or resource-constrained environments, etc.
  • Scaling Law: Scaling law of parameter, interaction, etc.
• Practical Applications
  • Toolkit: Platforms, codebases or software for developing and deploying social simulations with large language models.
  • Vertical Field: Applications in specific fields such as games and virtual worlds, healthcare and medicine, education, and other domain-specific use cases where social simulations and agent-based models are valuable.
• Ethical Considerations: Ethics, risks, bias and fairness, etc.