Metraipolis › archive › dc_153b2f786d83

Certifying Collective Reasoning in Multi-Agent Systems via Koopman Spectral Analysis — arXiv:2608.05956

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05956
License (as archived)
CC0-1.0
Archived
2026-10-25T20:48:32.957Z
SHA-256 of the archived text
19a204b3bee3ce1b6d30f534616a56ab4d364487ab4159144702aecffcdb5d1e
Stable URL of this page
https://metraipolis.com/documento/dc_153b2f786d83

How to cite

Certifying Collective Reasoning in Multi-Agent Systems via Koopman Spectral Analysis — arXiv:2608.05956 — arXiv (en), https://arxiv.org/abs/2608.05956 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_153b2f786d83 (Metraipolis archive dc_153b2f786d83, sha256 19a204b3bee3ce1b6d30f534616a56ab4d364487ab4159144702aecffcdb5d1e)
BibTeX
@misc{dc153b2f786d83,
  title = {Certifying Collective Reasoning in Multi-Agent Systems via Koopman Spectral Analysis — arXiv:2608.05956},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05956},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_153b2f786d83; sha256 19a204b3bee3ce1b6d30f534616a56ab4d364487ab4159144702aecffcdb5d1e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05956. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Orchestrated collectives of large language model (LLM) agents that debate and vote are an emerging form of computational intelligence: the intelligent behaviour resides in the \emph{interaction}, not in any single agent. They improve task accuracy, yet remain black boxes at the system level: there is no principled test of convergence, no bound on the rounds needed, and no faithful account of what drove a decision. This paper develops a novel framework based on Koopman operator theory and validates its theoretical guarantees on multi-agent consensus dynamics. Treating the collective as one nonlinear dynamical system on a communication graph, we read its essential behaviour off the spectrum of its Koopman transfer operator, an exact linear representation of the nonlinear dynamics estimated from interaction traces. The spectrum yields three machine-checkable certificates: the sub-dominant eigenvalue $\lambda_2$ fixes the intrinsic timescale of reasoning and yields a convergence deadline computable \emph{before} the debate runs; its eigenvector names the coherent factions the collective reasons in, and $|\lambda_2|$ certifies when that explanation is valid; and the leading spectral coordinates form a compressed, auditable message basis. On an attention-consensus model, the deadline tracks observed convergence with log--log correlation $0.93$ and bounds it in 96\% of 24 configurations; attribution is exact whenever the spectrum certifies metastability; eight of 32 coordinates preserve the decision at 99.7\% fidelity; and a certificate learned from 15 debates held on 60/60 held-out debates. The study runs in minutes on a CPU, making spectral certification a practical layer for trustworthy collective reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2608.05956 — 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 2026-10-25T20:47:44.136Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).