mlsanityData to 14 Oct 2026

SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation

arXiv 2504.16122 ↗First posted 19 Apr 2025cs.CY cs.AIcited by 10

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Social simulation through large language model (LLM) agents is a promising approach to explore and validate hypotheses related to social science questions and LLM agents behavior. We present SOTOPIA-S4, a fast, flexible, and scalable social simulation system that addresses the technical barriers of current frameworks while enabling practitioners to generate multi-turn and multi-party LLM-based interactions with customizable evaluation metrics for hypothesis testing. SOTOPIA-S4 comes as a pip package that contains a simulation engine, an API server with flexible RESTful APIs for simulation management, and a web interface that enables both technical and non-technical users to design, run, and analyze simulations without programming. We demonstrate the usefulness of SOTOPIA-S4 with two use cases involving dyadic hiring negotiation and multi-party planning scenarios.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 17 of its 33 references that are in the map. First posted on arXiv 19 Apr 2025.

Builds on

17 of 33 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals15 Nov
  2. 2024Evolution of Social Norms in LLM Agents using Natural Language2 Sep
  3. 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis8 Feb
  4. 2023Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia6 Dec
  5. 2023MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming10 Oct
  6. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 11

  1. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  2. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 367
  3. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 180
  4. 2024Large Language Models are Inconsistent and Biased Evaluatorscited by 153
  5. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 132
  6. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 97
  7. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agentscited by 93
  8. 2024Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMscited by 59
  9. 2024Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulationcited by 46
  10. 2024HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactionscited by 44
  11. 2024Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personascited by 37

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 7.

10 papers.

  1. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 14
  2. 2025YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Modelscited by 11
  3. 2026PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimizationcited by 10
  4. 2026One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligencecited by 7
  5. 2025Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communicationcited by 4
  6. 2026How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?cited by 3
  7. 2026Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformationcited by 2
  8. 2026HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patternscited by 2
  9. 2026Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studiescited by 1
  10. 2026MiroBench: Benchmarking Realism in Agentic Simulation of Real-world Discussionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users
  2. 2025Exploring Large Language Model Agents for Piloting Social Experiments
  3. 2024LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities
  4. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents
  5. 2024GenSim: A General Social Simulation Platform with Large Language Model based Agents
  6. 2026LLM Agents as Social Scientists: A Human-AI Collaborative Platform for Social Science Automation
  7. 2024Sense and Sensitivity: Evaluating the simulation of social dynamics via Large Language Models
  8. 2026EASE Configuration Facilitates A Reproducible Science of LLM Social Simulations