Metraipolis › archive › dc_18e211f7fbec
Consensus and Factual Dynamics in Large Populations of Interacting Language Models — arXiv:2609.39211
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39211
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:39:32.724Z
- SHA-256 of the archived text
3b610c24bdd71f8d397fd2ad44a17f316854a848ff5ed0472aeeee28bc064dfb- Stable URL of this page
https://metraipolis.com/documento/dc_18e211f7fbec
How to cite
Consensus and Factual Dynamics in Large Populations of Interacting Language Models — arXiv:2609.39211 — arXiv (en), https://arxiv.org/abs/2609.39211 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_18e211f7fbec (Metraipolis archive dc_18e211f7fbec, sha256 3b610c24bdd71f8d397fd2ad44a17f316854a848ff5ed0472aeeee28bc064dfb)
BibTeX
@misc{dc18e211f7fbec,
title = {Consensus and Factual Dynamics in Large Populations of Interacting Language Models — arXiv:2609.39211},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39211},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_18e211f7fbec; sha256 3b610c24bdd71f8d397fd2ad44a17f316854a848ff5ed0472aeeee28bc064dfb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39211. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Model (LLM) agents are increasingly deployed as populations of interacting entities, in which consensus --agreement on a shared answer-- emerges as a collective, unengineered behaviour. Prior work on LLM consensus shows that agents can cross-verify their answers and converge towards more factual responses, treating agreement as a proxy for correctness. However, these studies usually fix a single interaction structure, leaving open how consensus depends on how agents interact. We address this gap by introducing RHEON, a physics-inspired framework that recasts a population drawn from a single frozen model as an evolving $O(n)$ spin system on a ladder of interaction geometries of increasing effective dimension --from a 1D ring to a full-coupling mean-field graph-- with the sampling temperature $T$ as the tunable source of thermal disorder, evolved through a Glauber-like asynchronous dynamics. Sweeping RHEON across $432$ configurations of prompt, population size, communication topology, and sampling temperature yields Eraclitus-4.7M, a tagged evolutionary corpus of $4.7$ million responses. We find that agents reach their strongest consensus gain within the first few update sweeps and that increasing the number of neighbours per agent accelerates convergence on average. We further show that whether a configuration settles on factually correct or hallucinated consensus is not predictable from its initial state alone, and that the hallucination-minimising temperature depends on how the agents are coupled, so the common near-greedy default is not automatically the safest. Finally, semantic agreement correlates positively with factual convergence, and interaction strengthens the association, yet never enough for unanimity to certify correctness. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.39211 — 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 2026-10-07T12:12:18.631Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).