# The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS

DevFeed: [The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS](<https://devfeed.tech/articles/the-hitchhiker-s-guide-to-system-1-models-fast-decision-making-beyond-llms-107933.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.33775>)

Author: Haggai Roitman

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [bias](<https://devfeed.tech/tags/bias.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [domains](<https://devfeed.tech/tags/domains.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [fast](<https://devfeed.tech/tags/fast.md>), [guide](<https://devfeed.tech/tags/guide.md>), [inference](<https://devfeed.tech/tags/inference.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [llms](<https://devfeed.tech/tags/llms.md>), [system-1-models](<https://devfeed.tech/tags/system-1-models.md>)

## AI overview

System 1 decision models map inputs to typed, structured decisions in one forward pass, targeting routine tasks such as routing, gating, scoring, and classification where sub-second latency matters. The guide groups these models into five families--encoder-based classifiers, reward models, non-autoregressive decision engines, contrastive decision models, and extraction models--and covers their architectures, training, and deployment trade-offs. It emphasizes calibration, including proper scoring rules, RLCD, IIA violations, ordinal-scale bias, and few-shot recalibration under distribution shift. For agentic workflows, it describes using these models as decision infrastructure and cascading between fast System 1 and slower System 2 models based on calibrated confidence. The abstract also says the guide includes application domains, runnable code, an open-source model zoo, a practitioner checklist, and self-assessment questions.

## Source excerpt

arXiv:2610.33775v2 Announce Type: replace Abstract: 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.