Metraipolis › archive › dc_ea23615f1f8a
Network Topology Does Not Matter: The Breakdown of Classical Consensus in LLM Populations — arXiv:2610.37699
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.37699
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:06:38.492Z
- SHA-256 of the archived text
2d7b9ee9120013dc420e5bac4d1f0b2ecd1e5fe7664c1378258f6ef7007658e7- Stable URL of this page
https://metraipolis.com/documento/dc_ea23615f1f8a
How to cite
Network Topology Does Not Matter: The Breakdown of Classical Consensus in LLM Populations — arXiv:2610.37699 — arXiv (en), https://arxiv.org/abs/2610.37699 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea23615f1f8a (Metraipolis archive dc_ea23615f1f8a, sha256 2d7b9ee9120013dc420e5bac4d1f0b2ecd1e5fe7664c1378258f6ef7007658e7)
BibTeX
@misc{dcea23615f1f8a,
title = {Network Topology Does Not Matter: The Breakdown of Classical Consensus in LLM Populations — arXiv:2610.37699},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.37699},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea23615f1f8a; sha256 2d7b9ee9120013dc420e5bac4d1f0b2ecd1e5fe7664c1378258f6ef7007658e7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37699. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As multi-agent language model networks become widely deployed, predicting their collective behavior is a critical challenge. Classical distributed consensus theory relies on network topology to predict convergence, structurally assuming that agent updates are convex combinations, population means are conserved, and weights are content-independent. In this work, we demonstrate that these foundational assumptions fail for large language models (LLMs). By deterministically extracting continuous credence from token-level probabilities across eight instruction-tuned models and 73,080 controlled exchanges, we directly measure the empirical LLM update operator. We find that LLMs systematically violate convexity by updating outside the hull of observed opinions, exhibiting active repulsion (negative weights) that fundamentally breaks row-stochastic modeling and standard bounded-confidence repairs. Scaling these empirically fitted operators to simulations of 10,000 agents reveals that algebraic connectivity explains almost none of the final outcome variance. Instead, population dynamics are governed entirely by the model's internal update bias and message framing. Consequently, populations of several models, including those with up to 7B parameters, reliably compound small local drifts to reach confident agreement on objectively false claims regardless of their network structure. Our results prove that classical graph-theoretic metrics are inadequate for LLM populations, highlighting a profound deployment risk where multi-agent deliberation predictably saturates in collective delusion. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.37699 — 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 2026-10-31T06:06:38.399Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).