about
The Hitchhiker's Guide to System One Models (arxiv.org)
2 points by saikatsg 18 days ago | hide | past | pdf | discuss on HN

In plain words: A guide to fast decision models that turn an input into a choice in one step, unlike language models that write answers word by word. It sorts them into five families and shows how to make their confidence scores trustworthy across 18 uses.

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

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.

Haggai Roitman
arXiv:2610.33775 · cs.AI, cs.CL · submitted Oct 24, 2026 · updated Oct 29, 2026
abstract · pdf · html · version 1.1 - fixes to references/some content fixes

add comment on HN