# Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses

**Published:** October 5, 2026
**Author:** Jiawei Li
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/fast-models-slow-evidence-a-paired-and-self-audited-evaluation-of-system

Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input carries an injection. System-1 decision models answer such questions in a single forward pass with class probabilities,…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.02267)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*