Generative AI collective behavior needs an interactionist paradigm
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912826464927744 |
|---|---|
| author | Ferrarotti, Laura Campedelli, Gian Maria Dessì, Roberto Baronchelli, Andrea Iacca, Giovanni Carley, Kathleen M. Pentland, Alex Leibo, Joel Z. Evans, James Lepri, Bruno |
| author_facet | Ferrarotti, Laura Campedelli, Gian Maria Dessì, Roberto Baronchelli, Andrea Iacca, Giovanni Carley, Kathleen M. Pentland, Alex Leibo, Joel Z. Evans, James Lepri, Bruno |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10567 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generative AI collective behavior needs an interactionist paradigm Ferrarotti, Laura Campedelli, Gian Maria Dessì, Roberto Baronchelli, Andrea Iacca, Giovanni Carley, Kathleen M. Pentland, Alex Leibo, Joel Z. Evans, James Lepri, Bruno Artificial Intelligence Computers and Society Human-Computer Interaction Machine Learning Multiagent Systems 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. |
| title | Generative AI collective behavior needs an interactionist paradigm |
| topic | Artificial Intelligence Computers and Society Human-Computer Interaction Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2601.10567 |