Metraipolis › archive › dc_d2550426a07f
The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS — arXiv:2610.33775
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.33775
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:57:21.585Z
- SHA-256 of the archived text
01c272f629d4d818957b37a89559d8fbb233a0eee9227f4f9a4bad57791dd056- Stable URL of this page
https://metraipolis.com/documento/dc_d2550426a07f
How to cite
The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS — arXiv:2610.33775 — arXiv (en), https://arxiv.org/abs/2610.33775 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2550426a07f (Metraipolis archive dc_d2550426a07f, sha256 01c272f629d4d818957b37a89559d8fbb233a0eee9227f4f9a4bad57791dd056)
BibTeX
@misc{dcd2550426a07f,
title = {The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS — arXiv:2610.33775},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.33775},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2550426a07f; sha256 01c272f629d4d818957b37a89559d8fbb233a0eee9227f4f9a4bad57791dd056},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33775. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Models excel at reasoning and generation but their autoregressive, token-by-token inference makes them unnecessarily slow, expensive, and poorly calibrated for the many routine decisions (routing, gating, scoring, classification) that modern AI systems require at sub-second latency. A growing class of models addresses this gap: System 1 decision models, architectures that map an input directly to a typed, structured decision in a single forward pass. This guide provides a comprehensive, practitioner-oriented treatment of the field. We propose a five-family taxonomy covering encoder-based classifiers, reward models, non-autoregressive decision engines, contrastive decision models, and extraction models, and we provide in-depth coverage of each family's architecture, training methodology, and deployment trade-offs. A central theme is calibration: we develop the theory of proper scoring rules, analyze Reinforcement Learning for Calibrated Decisions (RLCD), and examine recently discovered phenomena including IIA violations, ordinal-scale bias, and few-shot recalibration under distribution shift. On the integration side, we describe how System 1 models serve as decision infrastructure within agentic workflows and System 1 + System 2 cascades that route between fast and slow models based on calibrated confidence. The guide covers 18 application domains, maps the rapidly growing open-source ecosystem (over 70 model reproductions in weeks), provides runnable code throughout, and includes a practitioner's checklist, an open-source model zoo, and 22 self-assessment questions with detailed answers. Spanning 190 references, it is intended as a unified entry point for researchers and engineers working at the intersection of fast decision-making, calibration, and production AI systems. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.33775 — 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 2026-10-27T07:55:30.666Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).