Skip to yearly menu bar Skip to main content

Workshop Fri, Oct 9, 2026 • 8:30 AM – 6:00 PM PDT Imperial Ballroom A

Social Sim'26: Fidelity in Applications

Zachary Yang ⋅ Maximilian Puelma Touzel ⋅ Xuhui Zhou ⋅ Yunze Xiao ⋅ Lynnette Hui Xian Ng ⋅ Jean-Francois Godbout ⋅ Reihaneh Rabbany ⋅ Maarten Sap

Project Page

Abstract

In an era where digital interactions increasingly shape our social fabric, LLM-based social simulation offers a powerful lens to understand complex societal dynamics. As the scope and ambition of these simulations expand, however, important methodological and conceptual challenges become increasingly salient. Beyond compelling demonstrations, questions remain around evaluation, robustness, interpretability, and empirical grounding. Now in its second iteration, our workshop invites researchers, practitioners, and thought leaders to explore rigorous and responsible approaches to LLM-based social simulation.

Youtube link: https://youtube.com/live/rmgv3LMR05g?feature=share

Chat is not available.

Schedule

Time zone: Conference local time zone

8:50 AM

Opening Remarks

Maximilian Puelma Touzel ⋅ Zachary Yang

9:00 AM

Person Simulation

Noah Goodman

9:30 AM

Spotlight Talks

Nguyen K Hoang ⋅ Dani Roytburg ⋅ Yujiao Chen

10:00 AM

Personalized Foundation Model for Social Simulation

Zhongyu Wei

10:30 AM

LLM-negotiated joint programmes of government

Slava Jankin

11:00 AM

Coffee Break

11:15 AM

Multi-Turn Reinforcement Learning for Real-World Dialogue Agents

Marwa Abdulhai

11:45 AM

Poster Session

→ PB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO

Jim Wang ⋅ Jun Yin ⋅ Xu Han ⋅ Yongsheng Mei ⋅ Jie Hao ⋅ Bin Guo

→ Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

Chenguang Wang ⋅ Ming Li ⋅ Xinyue Zeng ⋅ Zhuochun Li ⋅ Hong Jiao ⋅ Tianyi Zhou ⋅ Dawei Zhou

→ Simulating Aggregate Electoral Opinion Trajectories with LLM Personas and Media Exposure

Jaywoong Jeong ⋅ Robin Na

→ Position: Synthetic Persona Needs Explicit Grounding and Standardized Reporting

Yucheng Lu ⋅ Xiaoyi Liu ⋅ Heming Liu ⋅ Hanwen Xing ⋅ Shirley Huang ⋅ Guanghui Min ⋅ Zhengyang Shan ⋅ My Chiffon Nguyen ⋅ Ishan Gupta ⋅ Zonglin Di ⋅ Qianfeng Wen ⋅ Yifan S Liu ⋅ Ruoqi Gao ⋅ Yilan Fan ⋅ Jianheng Hou ⋅ Brihi Joshi ⋅ Muhammad A Mohsin ⋅ Yunze Xiao ⋅ Keyang Xuan ⋅ Hannah Collison ⋅ Jintao Huang ⋅ Jiatong Li ⋅ Sankalp Jajee ⋅ Yunhan Zhao ⋅ Bing Hu ⋅ Zhiwei Zhang ⋅ Sky Ng ⋅ Xupeng Chen ⋅ binghang lu ⋅ Weihang Xiao ⋅ Aravind Mohan ⋅ Bolun Sun ⋅ Yunshu Wu ⋅ Yuanda Xu ⋅ Yun Shen ⋅ Zheyuan Deng ⋅ Xincheng Tan ⋅ Qianyu Zhu ⋅ Dianzhuo Wang ⋅ Yijun Wang ⋅ Runyu Zhang ⋅ Yixuan He ⋅ Xiaomin Li ⋅ Yuexing Hao

→ Position: AI Is Not Ready for Strategic Conflicts

Mark Riedl ⋅ Glenn Matlin

→ Reason-Mediated Behavioral Models for Auditing LLM Social Simulators

Gautam Jajoo ⋅ Atharva Pandey

→ One Crowd, Three Cascades: Information Diffusion in LLM-Agent Simulations Is Governed by Serialization, Not Society

Tarun Raheja ⋅ Nilay Pochhi

→ Moral Hazard in Multi-Agent Language Models

Dane Malenfant

→ ECHO: Evidence-Calibrated Human Outcomes from Synthetic Users for Interaction Design

Dylan X Hou

→ Psychometric Framework for Comparing Alignment- Conditioned Behavior in Large Language Models

Krisha Arora ⋅ Anand Kumar Madasamy ⋅ Dishanth Arya

→ When the Generator Grades Itself: A Self-Judge Under-Flags Unsupported Outputs at Matched Scale in LLM Social Simulation

Rob Sneiderman

→ Tracing LLM Social Reasoning to Pretraining Data: A Provenance Audit for Social Simulation

Glenn Matlin ⋅ Chandreyi Chakraborty ⋅ Saehee Eom ⋅ Mika Okamoto ⋅ Rayan Castilla ⋅ Louis Jaburi ⋅ Alvin Deng ⋅ Taywon Min ⋅ Lucia Quirke ⋅ Stella Biderman ⋅ Mark Riedl

→ Social Choice Foundations for Simulation-Augmented Generation

Sonja Kraiczy ⋅ Smitha Milli ⋅ Ratip Emin Berker ⋅ Avinandan Bose ⋅ Brandon Amos ⋅ Jamelle Watson-Daniels ⋅ Maximilian Nickel ⋅ Edith Elkind ⋅ Ariel D Procaccia

→ Shall We Play a Game? Language Models for Open-ended Wargames

Glenn Matlin ⋅ Isaac Song ⋅ Yixiong Hao ⋅ Parv Mahajan ⋅ Evan Montoya ⋅ Ryan Bard ⋅ Stuart R Topp ⋅ Anthony Zang ⋅ Mohammed R Parwani ⋅ Soham Shetty ⋅ Mark Riedl

→ MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations

Sky Ng ⋅ Brihi Joshi ⋅ Ishan Gupta ⋅ Shirley Huang ⋅ Zonglin Di ⋅ Yun Shen ⋅ Qianfeng Wen ⋅ Yifan S Liu ⋅ Ruoqi Gao ⋅ Yilan Fan ⋅ Zhiwei Zhang ⋅ Muhammad A Mohsin ⋅ Yucheng Lu ⋅ Xiaoyi Liu ⋅ Heming Liu ⋅ Qianyu Zhu ⋅ Hanwen Xing ⋅ Zhengyang Shan ⋅ My Chiffon Nguyen ⋅ Guanghui Min ⋅ Jianheng Hou ⋅ Yunze Xiao ⋅ Keyang Xuan ⋅ Hannah Collison ⋅ Jintao Huang ⋅ Jiatong Li ⋅ Sankalp Jajee ⋅ Yunhan Zhao ⋅ Bing Hu ⋅ Xupeng Chen ⋅ binghang lu ⋅ Weihang Xiao ⋅ Aravind Mohan ⋅ Bolun Sun ⋅ Yunshu Wu ⋅ Yuanda Xu ⋅ Runyu Zhang ⋅ Zheyuan Deng ⋅ Xincheng Tan ⋅ Dianzhuo Wang ⋅ Yijun Wang ⋅ Yixuan He ⋅ Xiaomin Li ⋅ Yuexing Hao

→ Distinguishing Governance Effects from Prompting Artifacts in LLM Pricing Simulations

Theja Tulabandhula

→ Borrowing a Digital Twin: Grounding Individual-Level LLM Personas in a Matched Donor's Profile

Myungsu Kwak

→ Carryover Effect in LLM Personality Measurement

Yuehan Zhang ⋅ Xiao-Ming Wu

→ PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior

James Flemings ⋅ Murali Annavaram

→ Individually Sensible, Collectively Harmful: Simulating Commons Failure in LLM Societies

Yujiao Chen

→ Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents

Harshita Chopra ⋅ Kshitish Ghate ⋅ Aylin Caliskan ⋅ Tadayoshi Kohno ⋅ Chirag Shah ⋅ Natasha Jaques

→ Classic AI as Scaffolding for LLM Social Agents

Anatole Gershman

→ LifeBench: Evaluating Large Language Models as Lifelong Decision-Makers in a Simulated Human Life

Ishaan Bansal ⋅ Shivank Garg

→ No One Wins in Nuclear War: Social Simulations of High-stakes Military Decision-making

Glenn Matlin ⋅ Isaac Song ⋅ Anthony Zang ⋅ Mark Riedl

→ Disentangling Models from Personas in Heterogeneous LLM Simulations

Dani Roytburg ⋅ Daphne Ippolito

→ BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks

Jin Huang ⋅ Yutong Xie ⋅ Wanli Song ⋅ Xingjian Zhang ⋅ Walter M Yuan ⋅ Matthew O Jackson ⋅ Qiaozhu Mei

→ Activation-Steered Personas in Task-Oriented LLM Agent Simulations

Maryam Shoaeinaeini ⋅ Bernardo Rodrigues ⋅ Adib Mosharrof ⋅ A.B. Siddique ⋅ Brent Harrison

→ PersonaEval: Persona-Based User Simulation for Evaluating Interactive Applications

Yifan S Liu ⋅ Qianfeng Wen ⋅ Yilan Fan ⋅ Shirley Huang ⋅ Ruoqi Gao ⋅ Jianheng Hou ⋅ Muhammad A Mohsin ⋅ Zonglin Di ⋅ Brihi Joshi ⋅ Xincheng Tan ⋅ Yucheng Lu ⋅ Xiaoyi Liu ⋅ Heming Liu ⋅ Hanwen Xing ⋅ Guanghui Min ⋅ Zhengyang Shan ⋅ My Chiffon Nguyen ⋅ Ishan Gupta ⋅ Yunze Xiao ⋅ Hannah Collison ⋅ Jintao Huang ⋅ Jiatong Li ⋅ Sankalp Jajee ⋅ Yunhan Zhao ⋅ Bing Hu ⋅ Sky Ng ⋅ Xupeng Chen ⋅ binghang lu ⋅ Weihang Xiao ⋅ Aravind Mohan ⋅ Bolun Sun ⋅ Yunshu Wu ⋅ Yuanda Xu ⋅ Yun Shen ⋅ Runyu Zhang ⋅ Zheyuan Deng ⋅ Zhiwei Zhang ⋅ Qianyu Zhu ⋅ Dianzhuo Wang ⋅ Yijun Wang ⋅ Yixuan He ⋅ Yuexing Hao ⋅ Xiaomin Li

→ A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing

Jared Moore ⋅ Noah Goodman ⋅ Nick Haber ⋅ Max Kleiman-Weiner

→ Human-Simulation Interaction: From Prediction to Exploration in LLM Agent Simulations for Policy

Huanxing Chen

→ Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents

Yufeng Wang

→ Can LLMs Faithfully Enact Superforecaster Personas?

Andrew Williams ⋅ Evan Jiang ⋅ Martin Weiss ⋅ Nasim Rahaman ⋅ Hugo Larochelle

→ The Effect Of Warning Message Length on Language Model Simulated Response in Emergency Situations

Madeleine M Gagné ⋅ Arnav Jhala

→ SparkMe: Adaptive Semi-Structured Interviewing for Qualitative Insight Discovery

David Anugraha ⋅ Vishakh Padmakumar ⋅ Diyi Yang

→ LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment

Han Chen ⋅ Ming Li ⋅ Chenguang Wang ⋅ Yijun Liang ⋅ Dawei Zhou ⋅ Hong Jiao ⋅ Tianyi Zhou

→ For Questions of Ought, AI Could Use Some SAGE Advice

Smitha Milli ⋅ Ratip Emin Berker ⋅ Sonja Kraiczy ⋅ Claudia Shi ⋅ Jack Kussman ⋅ Avinandan Bose ⋅ Himaghna Bhattacharjee ⋅ Edith Elkind ⋅ Ariel D Procaccia ⋅ Maximilian Nickel

→ Social OMNI-EPIC: Learning-Progress-Driven Curriculum Generation for Social Interaction

Huijun Mao ⋅ Huanxing Chen ⋅ Nick Haber

→ Optimizing Behavioral Experiment Design with In-Silico Simulations

Sanchaita Hazra ⋅ Pao Siangliulue ⋅ Bodhisattwa Prasad Majumder ⋅ Peter Clark ⋅ Amy Zhang ⋅ Joseph Chee Chang

→ Everyone Conforms, No One Believes: Pluralistic Ignorance in LLM Agent Populations

Yashwanth YS

→ Synonymix: Unified Group Personas for Generative Simulations

Huanxing Chen ⋅ Aditesh Kumar

→ More Context Is Not Validation: A Baseline-First Audit of Action-Grounded LLM Listener Agents

Chinmay Rawat ⋅ Taaha Kazi ⋅ Vasu Sharma

→ PSI-Bench: Towards Clinically Grounded and Interpretable Evaluation of Depression Patient Simulators

Nguyen K Hoang ⋅ Shuhaib Mehri ⋅ Tse-An Hsu ⋅ Yi-Jyun Sun ⋅ Quynh X Truong ⋅ Khoa D Doan ⋅ Dilek Hakkani-Tür

→ LLM-Augmented Agent-Based Simulation of Cyber Social Agents

Lynnette Hui Xian Ng ⋅ Kathleen M Carley

→ Measuring Mutual Confirmation Bias Amplification in Simulated User-AI Dialogue: A Multi-Agent Simulation Frame- work

Reiko Tanabe

→ Role Steering of Language Models for Social Simulations

Isaac Song ⋅ Mohammed R Parwani ⋅ Glenn Matlin ⋅ Emile T Anand ⋅ Akhil Theerthala ⋅ Arjun Chatterjee ⋅ Anthony Zang ⋅ Maria Kostylew ⋅ Yonadav G Shavit ⋅ Sebastien Krier ⋅ Mark Riedl

→ Learning User Simulators with Turing Rewards

Susan Wang ⋅ Cedegao Zhang ⋅ Linlu Qiu ⋅ Zexue He ⋅ Pengyuan Li ⋅ Alex Pentland ⋅ Roger P Levy ⋅ Yoon Kim

→ Simile Demo: Behavioral Simulation for Enterprise

Sarah Chen

1:00 PM

Lunch

2:00 PM

Concordia: Generative Agent-Based Modelling for Social Science

Logan Cross

2:30 PM

Breakout Session

Maximilian Puelma Touzel ⋅ Zachary Yang ⋅ Yunze Xiao

3:30 PM

Coffee Break

3:50 PM

Panel

Noah Goodman ⋅ Zhongyu Wei ⋅ Slava Jankin ⋅ Marwa Abdulhai ⋅ Sarah Chen ⋅ Logan Cross

5:00 PM

Closing

Maximilian Puelma Touzel ⋅ Zachary Yang