mlsanityData to 14 Oct 2026

SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents

arXiv 2310.11667 ↗First posted 18 Oct 2023cs.AI cs.CL cs.LGcited by 367

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Humans are social beings; we pursue social goals in our daily interactions, which is a crucial aspect of social intelligence. Yet, AI systems' abilities in this realm remain elusive. We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and evaluate their social intelligence. In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We simulate the role-play interaction between LLM-based agents and humans within this task space and evaluate their performance with a holistic evaluation framework called SOTOPIA-Eval. With SOTOPIA, we find significant differences between these models in terms of their social intelligence, and we identify a subset of SOTOPIA scenarios, SOTOPIA-hard, that is generally challenging for all models. We find that on this subset, GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills. These findings demonstrate SOTOPIA's promise as a general platform for research on evaluating and improving social intelligence in artificial agents.

Key facts. Cited by 367 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 41 of its 94 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

41 of 94 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Gentopia: A Collaborative Platform for Tool-Augmented LLMs8 Aug
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 39

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  5. 2023Large Language Models are not Fair Evaluatorscited by 1,085
  6. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  7. 2020Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamicscited by 425
  8. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 339
  9. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 301
  10. 2023Role-Play with Large Language Modelscited by 294
  11. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 275
  12. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
27 more
  1. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 255
  2. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
  3. 2013The Complexity of Decentralized Control of Markov Decision Processescited by 231
  4. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 209
  5. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 209
  6. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 207
  7. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 207
  8. 2020"Other-Play" for Zero-Shot Coordinationcited by 198
  9. 2021TEACh: Task-driven Embodied Agents that Chatcited by 197
  10. 2023GPT detectors are biased against non-native English writerscited by 178
  11. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 163
  12. 2018Decoupling Strategy and Generation in Negotiation Dialoguescited by 162
  13. 2019Learning to Speak and Act in a Fantasy Text Adventure Gamecited by 122
  14. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 97
  15. 2021Challenges in Automated Debiasing for Toxic Language Detectioncited by 96
  16. 2023Wider and Deeper LLM Networks are Fairer LLM Evaluatorscited by 94
  17. 2022Evaluating Human-Language Model Interactioncited by 92
  18. 2020You Impress Me: Dialogue Generation via Mutual Persona Perceptioncited by 85
  19. 2023NormBank: A Knowledge Bank of Situational Social Normscited by 60
  20. 2017Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddingscited by 59
  21. 2020Social diversity and social preferences in mixed-motive reinforcement learningcited by 49
  22. 2021Few-shot Language Coordination by Modeling Theory of Mindcited by 32
  23. 2023Computational Language Acquisition with Theory of Mindcited by 15
  24. 2022Interactive Evaluation of Dialog Track at DSTC9cited by 9
  25. 2021SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agentscited by 7
  26. 2023The Open-domain Paradox for Chatbots: Common Ground as the Basis for Human-like Dialoguecited by 4
  27. 2022How "open" are the conversations with open-domain chatbots? A proposal for Speech Event based evaluationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 76; 2025: 116; 2026: 168.

367 papers.

Sort:

By area:

  1. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  2. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  3. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 494
  4. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 465
  5. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Taskscited by 326
  6. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
  7. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 230
  8. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  9. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 186
  10. 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Actioncited by 171
  11. 2023Simulating Opinion Dynamics with Networks of LLM-based Agentscited by 154
  12. 2024Direct Preference Optimization of Video Large Multimodal Models from Language Model Rewardcited by 147
38 more
  1. 2024Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systemscited by 133
  2. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 132
  3. 2023Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordiacited by 126
  4. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  5. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
  6. 2025Agentic Large Language Models, a surveycited by 108
  7. 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysiscited by 100
  8. 2024On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agentscited by 99
  9. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  10. 2024The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Modelscited by 93
  11. 2024A Survey on Self-Evolution of Large Language Modelscited by 91
  12. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 82
  13. 2025LLM Generated Persona is a Promise with a Catchcited by 81
  14. 2025OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safetycited by 75
  15. 2024Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulationcited by 71
  16. 2024Can Large Language Model Agents Simulate Human Trust Behavior?cited by 64
  17. 2024Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theorycited by 60
  18. 2024Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluationcited by 58
  19. 2024OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Modelscited by 54
  20. 2026Mind the Sim2Real Gap in User Simulation for Agentic Taskscited by 54
  21. 2024EmoBench: Evaluating the Emotional Intelligence of Large Language Modelscited by 53
  22. 2024Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactionscited by 51
  23. 2024SocialBench: Sociality Evaluation of Role-Playing Conversational Agentscited by 50
  24. 2024Evaluating Language Model Agency through Negotiationscited by 48
  25. 2025Agentic Reinforcement Learning with Implicit Step Rewardscited by 47
  26. 2024Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulationcited by 46
  27. 2024Werewolf Arena: A Case Study in LLM Evaluation via Social Deductioncited by 45
  28. 2024Exploring Prosocial Irrationality for LLM Agents: A Social Cognition Viewcited by 38
  29. 2023Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environmentcited by 37
  30. 2024ResearchTown: Simulator of Human Research Communitycited by 37
  31. 2023Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMscited by 36
  32. 2024Data-driven Discovery with Large Generative Modelscited by 34
  33. 2024Can Language Models Reason about Individualistic Human Values and Preferences?cited by 34
  34. 2024LLMs generate structurally realistic social networks but overestimate political homophilycited by 33
  35. 2024AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agentscited by 31
  36. 2025SDPO: Segment-Level Direct Preference Optimization for Social Agentscited by 30
  37. 2024Network Formation and Dynamics Among Multi-LLMscited by 29
  38. 2025LLM-Based Human-Agent Collaboration and Interaction Systems: A Surveycited by 29

50 most cited of 367 All 367 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents
  2. 2024AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios
  3. 2024Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level
  4. 2026Communicate-Predict-Act: Evaluating Social Intelligence of Agents
  5. 2024AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents
  6. 2025Social Cooperation in Conversational AI Agents
  7. 2025The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation
  8. 2026SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems