Metraipolis › archive › dc_3fbc71fbaf1e

Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents — arXiv:2610.02654

Source
arXiv
Original
https://arxiv.org/abs/2610.02654
License (as archived)
CC0-1.0
Archived
2026-10-05T22:48:03.838Z
SHA-256 of the archived text
589ec7b0692a57a22b15b46a0a91aea8d6dcb4bffa1170146110f61cc4c7489d
Stable URL of this page
https://metraipolis.com/documento/dc_3fbc71fbaf1e

How to cite

Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents — arXiv:2610.02654 — arXiv, https://arxiv.org/abs/2610.02654 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fbc71fbaf1e (Metraipolis archive dc_3fbc71fbaf1e, sha256 589ec7b0692a57a22b15b46a0a91aea8d6dcb4bffa1170146110f61cc4c7489d)
BibTeX
@misc{dc3fbc71fbaf1e,
  title = {Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents — arXiv:2610.02654},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02654},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fbc71fbaf1e; sha256 589ec7b0692a57a22b15b46a0a91aea8d6dcb4bffa1170146110f61cc4c7489d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02654. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Models of social contagion usually assume how individuals adopt beliefs and derive population behavior from it. We instead empirically measure belief adoption in language model agents, quantifying the probability an agent adopts a claim given how many peers endorse it. We find this adoption kernel to be sigmoid, a characteristic of complex contagion, with a threshold that is sensitive to three sources: the claim's plausibility, the source's reliability, and the agent's disposition. These three dimensions are well approximated by a single effective dimension which we propose can be understood as the coherence of the incoming belief with the LLM agent's prior beliefs. Further, we observe a characteristic of complex contagion in the collective dynamics of belief adoption in a system of AI agents: further spread on clustered than random networks. These systems also exhibit a bifurcating cascade window, and self-sustaining hysteretic consensus which lead to consensus being far harder to remove than to establish.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA); Social and Information Networks (cs.SI).
Pagina del lavoro: https://arxiv.org/abs/2610.02654 — 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 2026-10-05T22:45:40.641Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).