Generative AI collective behavior needs an interactionist paradigm

2026-01-15

AI Summary

This study addresses the emergent collective behaviors and societal implications of large language model (LLM) agents in group interactions. Recognizing that existing research often overlooks the interplay among pre-trained knowledge, implicit social priors, and dynamic social contexts, this work proposes interactionism as a novel theoretical paradigm to integrate in-context learning capabilities, knowledge representation, and modeling of social priors. Building on this foundation, the project establishes a new analytical framework tailored for generative AI multi-agent systems. It outlines four key research directions aimed at elucidating the mechanisms underlying emergent collective intelligence, informing the design of such systems, and fostering interdisciplinary dialogue across artificial intelligence, cognitive science, and social theory.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• collective behavior
• large language models
• emergent phenomena
• social context
• generative AI

Innovation

• interactionist paradigm
• large language models
• collective behavior
• in-context learning
• emergent phenomena