Metraipolis › archive › dc_66f38dbafc99

Stochastic Dynamics of Generative AI: From Autoregressive Models to Interacting LLM Networks and Neural SDEs — arXiv:2611.07065

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07065
License (as archived)
CC0-1.0
Archived
2026-11-06T14:44:03.667Z
SHA-256 of the archived text
01082d44d668a15b7e675579e424682141a407a54370ac855a79f114be5dc246
Stable URL of this page
https://metraipolis.com/documento/dc_66f38dbafc99

How to cite

Stochastic Dynamics of Generative AI: From Autoregressive Models to Interacting LLM Networks and Neural SDEs — arXiv:2611.07065 — arXiv (en), https://arxiv.org/abs/2611.07065 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_66f38dbafc99 (Metraipolis archive dc_66f38dbafc99, sha256 01082d44d668a15b7e675579e424682141a407a54370ac855a79f114be5dc246)
BibTeX
@misc{dc66f38dbafc99,
  title = {Stochastic Dynamics of Generative AI: From Autoregressive Models to Interacting LLM Networks and Neural SDEs — arXiv:2611.07065},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07065},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_66f38dbafc99; sha256 01082d44d668a15b7e675579e424682141a407a54370ac855a79f114be5dc246},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07065. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper develops a stochastic dynamical-systems perspective on three classes of generative AI models. First, we formulate large language models (LLMs) as high-dimensional nonlinear autoregressive models with attention-based dependencies. This formulation connects pretraining by conditional maximum likelihood to sequential token generation and provides a probabilistic interpretation of LLM operation. Second, we consider networks of interacting LLMs and characterize their collective behavior through mean-field ordinary differential equations. These dynamics provide a framework for understanding emergent preferential attachment and persistent structural biases, including type-dependent glass-ceiling effects. Third, we consider neural stochastic differential equations (SDEs) as continuous-time generative models for stochastic trajectories, including those observed at irregular time intervals. We discuss their training with particular emphasis on Wiener-space cubature methods based on rough-path analysis as an efficient alternative to Monte Carlo estimation. Together, the three settings address probabilistic prediction, information exchange and emergent behavior in interacting networks, and path-space generative modeling.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Signal Processing (eess.SP); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2611.07065 — 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 2026-11-06T14:21:42.611Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).