Metraipolis › archive › dc_c82d339362be
Collective Regimes in Multi-Agent LLMs under Reasoning Effort and Communication Topology — arXiv:2609.35885
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35885
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:21:11.623Z
- SHA-256 of the archived text
59bf5fd66fd59519c0e0fbf8f0ab9e7c57562c65378a7311690aaa4f9c6c59d5- Stable URL of this page
https://metraipolis.com/documento/dc_c82d339362be
How to cite
Collective Regimes in Multi-Agent LLMs under Reasoning Effort and Communication Topology — arXiv:2609.35885 — arXiv (en), https://arxiv.org/abs/2609.35885 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c82d339362be (Metraipolis archive dc_c82d339362be, sha256 59bf5fd66fd59519c0e0fbf8f0ab9e7c57562c65378a7311690aaa4f9c6c59d5)
BibTeX
@misc{dcc82d339362be,
title = {Collective Regimes in Multi-Agent LLMs under Reasoning Effort and Communication Topology — arXiv:2609.35885},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35885},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c82d339362be; sha256 59bf5fd66fd59519c0e0fbf8f0ab9e7c57562c65378a7311690aaa4f9c6c59d5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35885. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent LLM systems are increasingly used for deliberation and evaluation, often under the assumption that greater peer interaction leads to more reliable consensus. Existing work largely evaluates these systems through final accuracy or aggregate agreement. However, such measures do not reveal how agreement is organized in the panel. In this paper, we study N = 50 stateless LLM agents that update their predictions from locally visible peers, and characterize their behavior using both global and local measurements of agreement. We identify three collective regimes: synchronised, twisted (locally ordered but globally incoherent) and chimera-like, where coherent and incoherent subpopulations coexist. Increasing reasoning effort in gpt-5-mini shifts panels from variable, often fragmented outcomes toward locally ordered twisted states, and a small follow-up shows such states can also form from permuted initial conditions, whereas increasing communication connectivity drives them toward global synchronisation. Fragmentation collapses faster as algebraic connectivity increases across rewired graphs. The topology effect also appears on a non-circular judging task and across models from three providers. Finally, low spatial heterogeneity does not guarantee global consensus: 40% of trials with Delta Z below 0.03 retain a twisted configuration through the final 20 turns. These results show that reasoning effort and communication topology control different aspects of multi-agent coordination, and that aggregate agreement alone is insufficient to characterize collective LLM behavior. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.35885 — 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 2026-10-07T15:54:11.781Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).