mlsanityData to 14 Oct 2026

Generative AI collective behavior needs an interactionist paradigm

arXiv 2601.10567 ↗First posted 15 Jan 2026cs.AI cs.CY cs.HCcited by 6

Not on the map. Why?

Abstract (arXiv)

In this article, we argue that understanding the collective behavior of agents based on large language models (LLMs) is an essential area of inquiry, with important implications in terms of risks and benefits, impacting us as a society at many levels. We claim that the distinctive nature of LLMs--namely, their initialization with extensive pre-trained knowledge and implicit social priors, together with their capability of adaptation through in-context learning--motivates the need for an interactionist paradigm consisting of alternative theoretical foundations, methodologies, and analytical tools, in order to systematically examine how prior knowledge and embedded values interact with social context to shape emergent phenomena in multi-agent generative AI systems. We propose and discuss four directions that we consider crucial for the development and deployment of LLM-based collectives, focusing on theory, methods, and trans-disciplinary dialogue.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 81 of its 154 references that are in the map. First posted on arXiv 15 Jan 2026.

Builds on

81 of 154 references.

References · 81

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  7. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  8. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  9. 2023LIMA: Less Is More for Alignmentcited by 1,100
  10. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  11. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  12. 2022Transformers learn in-context by gradient descentcited by 732
38 more
  1. 2022What learning algorithm is in-context learning? Investigations with linear modelscited by 684
  2. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  3. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 332
  4. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 290
  5. 2023A Survey of Reinforcement Learning from Human Feedbackcited by 264
  6. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
  7. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
  8. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 178
  9. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  10. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  11. 2019Feature relevance quantification in explainable AI: A causal problemcited by 167
  12. 2025Multi-Agent Risks from Advanced AIcited by 163
  13. 2022Interventional Causal Representation Learningcited by 142
  14. 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)cited by 141
  15. 2023Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordiacited by 126
  16. 2024Emergent social conventions and collective bias in LLM populationscited by 123
  17. 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learningcited by 100
  18. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 99
  19. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  20. 2020Compositional Languages Emerge in a Neural Iterated Learning Modelcited by 75
  21. 2025Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agentscited by 71
  22. 2023Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithmscited by 65
  23. 2020The COVID-19 Social Media Infodemiccited by 64
  24. 2024Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?cited by 63
  25. 2019Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Researchcited by 61
  26. 2019Anti-efficient encoding in emergent communicationcited by 59
  27. 2025Reinforcement Learning from Human Feedbackcited by 58
  28. 2024Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Methodcited by 55
  29. 2022Transformers generalize differently from information stored in context vs in weightscited by 49
  30. 2023Welfare Diplomacy: Benchmarking Language Model Cooperationcited by 45
  31. 2020Emergent Social Learning via Multi-agent Reinforcement Learningcited by 44
  32. 2025Learning without training: The implicit dynamics of in-context learningcited by 43
  33. 2016The State of Applied Econometrics - Causality and Policy Evaluationcited by 41
  34. 2024Emergence of Social Norms in Generative Agent Societies: Principles and Architecturecited by 41
  35. 2025Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agentscited by 41
  36. 2022Melting Pot 2.0cited by 40
  37. 2020Causal Inference under Networked Interference and Intervention Policy Enhancementcited by 38
  38. 2021Collective Intelligence for Deep Learning: A Survey of Recent Developmentscited by 34

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Collective Behavior of AI Agents: the Case of Moltbookcited by 13
  2. 2026When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook Communitycited by 3
  3. 2026When AI Agents Learn from Each Other: Insights from Emergent AI Agent Communities on OpenClaw for Human-AI Partnership in Educationcited by 1
  4. 2026A Note on the Strategic Confinement Problemcited by 1
  5. 2026Conversable Complexity: Agentic LLM Collectives as Interpretable Substratescited by 1
  6. 2026The Hermon Moment: AI Self-Transcendence and Its Human Narrationcited by 0