mlsanityData to 13 Oct 2026

AI Agent Behavioral Science

arXiv 2506.06366 ↗First posted 4 Jun 2025q-bio.NC cs.CY cs.MAcited by 6

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

Abstract (arXiv)

Recent advances in large language models (LLMs) have enabled the development of AI agents that exhibit increasingly human-like behaviors, including planning, adaptation, and social dynamics across diverse, interactive, and open-ended scenarios. These behaviors are not solely the product of the internal architectures of the underlying models, but emerge from their integration into agentic systems operating within specific contexts, where environmental factors, social cues, and interaction feedbacks shape behavior over time. This evolution necessitates a new scientific perspective: AI Agent Behavioral Science. Rather than focusing only on internal mechanisms, this perspective emphasizes the systematic observation of behavior, design of interventions to test hypotheses, and theory-guided interpretation of how AI agents act, adapt, and interact over time. We systematize a growing body of research across individual agent, multi-agent, and human-agent interaction settings, and further demonstrate how this perspective informs responsible AI by treating fairness, safety, interpretability, accountability, and privacy as behavioral properties. By unifying recent findings and laying out future directions, we position AI Agent Behavioral Science as a necessary complement to traditional model-centric approaches, providing essential tools for understanding, evaluating, and governing the real-world behavior of increasingly autonomous AI systems.

Key facts. Cited by 6 papers in the map (data through 13 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 135 of its 217 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

135 of 217 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Investigating and Extending Homans' Social Exchange Theory with Large Language Model based Agents18 Feb
  2. 2024Identity-Driven Hierarchical Role-Playing Agents28 Jul
  3. 2024Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory20 Jun
  4. 2024Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents25 Apr
  5. 2024Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent21 Feb
  6. 2024Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents19 Feb
  7. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars28 Nov
  8. 2023The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents16 Nov
  9. 2023Simulating Opinion Dynamics with Networks of LLM-based Agents16 Nov
  10. 2023CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agents26 Oct
  11. 2023LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay23 Oct
  12. 2023EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities16 Oct
3 more
  1. 2023MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming10 Oct
  2. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View3 Oct
  3. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 120

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,549
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,091
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,986
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,363
  8. 2017Deep reinforcement learning from human preferencescited by 3,871
  9. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,949
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,028
  11. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,945
  12. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,531
38 more
  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,525
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,433
  3. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,410
  4. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  5. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 999
  6. 2022A Generalist Agentcited by 803
  7. 2023Whose Opinions Do Language Models Reflect?cited by 768
  8. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 750
  9. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 734
  10. 2020A Survey on Visual Transformercited by 654
  11. 2023Bias and Fairness in Large Language Models: A Surveycited by 636
  12. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 586
  13. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 549
  14. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
  15. 2023LaMP: When Large Language Models Meet Personalizationcited by 430
  16. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 311
  17. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 310
  18. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingcited by 275
  19. 2024Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoningcited by 271
  20. 2020Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depthcited by 241
  21. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 240
  22. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 239
  23. 2024ReFT: Reasoning with Reinforced Fine-Tuningcited by 237
  24. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 230
  25. 2023Playing repeated games with Large Language Modelscited by 216
  26. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 212
  27. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 204
  28. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 198
  29. 2024BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languagescited by 171
  30. 2023Cultural Bias and Cultural Alignment of Large Language Modelscited by 149
  31. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 147
  32. 2024Large language models that replace human participants can harmfully misportray and flatten identity groupscited by 141
  33. 2024Investigating Cultural Alignment of Large Language Modelscited by 141
  34. 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 139
  35. 2022Thinking Fast and Slow in Large Language Modelscited by 136
  36. 2024Token-level Direct Preference Optimizationcited by 135
  37. 2024Direct Preference Optimization with an Offsetcited by 122
  38. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 114

50 most cited of 120 All 120 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoningcited by 0
  2. 2026Agentic AI Autonomy Assessment: A Decision-Support Framework Towards Governed Supply Chain Systemscited by 0
  3. 2026SocialFiVis: A Visual Analytics Sandbox for LLM-Grounded Multi-Agent Simulation in Social Financecited by 0
  4. 2026Benchmarking large language model agent societies against human behavioural distributionscited by 0
  5. 2026The average-farmer illusion in language-model simulations of agricultural decisionscited by 0
  6. 2026Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpuscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Artificially intelligent agents in the social and behavioral sciences: A history and outlook
  2. 2026Preregistration for Experiments with AI Agents
  3. 2024Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective
  4. 2026Position: Behavioral Systems Require Behavioral Tests
  5. 2025Exploring Large Language Model Agents for Piloting Social Experiments
  6. 2026Questionnaire Responses Do not Capture the Safety of AI Agents
  7. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond
  8. 2023Do LLM Agents Exhibit Social Behavior?