Metraipolis › archive › dc_593cb5790561

Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents — arXiv:2608.16578

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16578
License (as archived)
CC0-1.0
Archived
2026-10-18T17:45:08.677Z
SHA-256 of the archived text
40abd85769391a72f987278f86af51529073e2bec0ce2f79d83150347bec43d4
Stable URL of this page
https://metraipolis.com/documento/dc_593cb5790561

How to cite

Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents — arXiv:2608.16578 — arXiv (en), https://arxiv.org/abs/2608.16578 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_593cb5790561 (Metraipolis archive dc_593cb5790561, sha256 40abd85769391a72f987278f86af51529073e2bec0ce2f79d83150347bec43d4)
BibTeX
@misc{dc593cb5790561,
  title = {Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents — arXiv:2608.16578},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16578},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_593cb5790561; sha256 40abd85769391a72f987278f86af51529073e2bec0ce2f79d83150347bec43d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16578. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting these collective dynamics is therefore important for designing effective and aligned multi-agent systems. Here, we study over 10,000 communities of language-model agents that repeatedly exchange messages and revise their opinions across objective mathematics questions and subjective political statements. Despite substantial diversity in possible behavior, the individual and group dynamics can be represented by three characteristic regimes: indifference, polarization, and consensus. AI agents start indifferent and build conviction as they interact. On objective questions, communication improves collective accuracy, while on subjective questions it often drifts group opinions toward the right in the political spectrum. We explain these observations with a statistical-mechanics formalism in which agents stochastically favor lower social pressure. Given only initial opinions, our model predicts individual trajectories, outperforms all standard baselines, generalizes to unseen community graphs, and reproduces the observed group archetype distributions. Our fitted model parameters reveal the mechanics underlying our key observations: i) communities operate below the critical social temperature, which explains conviction buildup; ii) attractive ties outweigh repulsive ones, which favors consensus; and iii) agents holding the correct answer exert the strongest pull, which drives truth-seeking. Overall, our results demonstrate that collective behavior of AI agents, like that of other complex systems, follows compact and predictive dynamical laws.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA); Social and Information Networks (cs.SI).
Pagina del lavoro: https://arxiv.org/abs/2608.16578 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.880Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).