Metraipolis › archive › dc_dc8ac5b52834
6G Reasoning Agent Societies: Composition, Scaling, and Consistency-Time Laws — arXiv:2610.34357
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34357
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:55:25.996Z
- SHA-256 of the archived text
82c4a65ea1af82ec7c53bdb1a6ea6c49d23069c370393e041515acabc96a2d7d- Stable URL of this page
https://metraipolis.com/documento/dc_dc8ac5b52834
How to cite
6G Reasoning Agent Societies: Composition, Scaling, and Consistency-Time Laws — arXiv:2610.34357 — arXiv (en), https://arxiv.org/abs/2610.34357 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc8ac5b52834 (Metraipolis archive dc_dc8ac5b52834, sha256 82c4a65ea1af82ec7c53bdb1a6ea6c49d23069c370393e041515acabc96a2d7d)
BibTeX
@misc{dcdc8ac5b52834,
title = {6G Reasoning Agent Societies: Composition, Scaling, and Consistency-Time Laws — arXiv:2610.34357},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34357},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc8ac5b52834; sha256 82c4a65ea1af82ec7c53bdb1a6ea6c49d23069c370393e041515acabc96a2d7d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34357. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Emerging 6G control planes would compose Large Language Model (LLM) agents that exchange interpreted conclusions, so hallucinations can propagate even over error-free transport. Recent architectures audit each message locally against the sender's observation mask, but isolated audits miss collective behavior. Modeling the agent society as a cellular sheaf, we establish three laws valid on arbitrary topologies. First, the \emph{composition law}: network-wide divergence exceeds the sum of per-agent audit scores by exactly their hidden total correlation. This blind spot masks up to 23\% of joint divergence and, because the declared signal cancels in the cognitive signal-to-noise ratio (SNR), overstates it by $1.14$\,dB purely through topology; the resulting trust inflation preserves valid consensus states but slows convergence. Second, the \emph{scaling law}: reconciliation decouples across metric counters, so the worst-connected dimension sets the pace. Consistency time grows for a society size $n$ as $\Omega(n^{2/d})$ on polynomial-growth topologies of degree $d$, and paths breach a $1$\,s near-real-time budget at $n^\ast=13$ agents, whereas expanders ($\Theta(1)$) and radius-3 local audits ($O(1)$, $\approx300$\,ms) stay bounded. Third, the \emph{consistency-time law}: the timing error from omitted correlations is one-sided and capped by the worst-measured link. These laws, validated on simulated topologies and deployed LLM societies, give provable worst-case latency ceilings for near-real-time operation.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Networking and Internet Architecture (cs.NI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.34357 — 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 2026-10-27T07:55:15.058Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).