cs.AINov 16, 2026

System 1 agents: a method for local, reliable and fast agentic AI

Authors: Eleftherios Tzanis, Michail E. Klontzas

Organizations: Artificial Intelligence and Translational Imaging (ATI) Lab, Department of Radiology, School of Medicine, University of Crete, Heraklion, Crete, Greece. · Division of Radiology, Department of Clinical Science Intervention and Technology (CLINTEC), Karolinska Institute, Huddinge, Sweden. · Department of Medical Imaging, University Hospital of Heraklion, Crete, Greece.

Abstract

Agentic artificial intelligence could automate analyses of sensitive clinical data, but current agents depend on large language models (LLMs). Cloud LLMs expose patient data. Local LLMs hallucinate, and an invented value in a tool call propagates through every later step. Here we present a method to build System 1 agents: local agents that call tools without generating text. A deterministic compiler turns each tool's schema and the request into multiple-choice questions whose options come from the request and the schema, then a one-pass decision model answers them. On 1,952 requests to 157 biomedical tools, the best System 1 agent chose the right tool, or correctly declined, for 97.0% of requests, significantly ahead of all 18 local LLM-agent settings (best 95.2%). The System 1 agent filled 97.0% of 6,056 stated argument values. No System 1 call contained invented content, against 5.5-19.7% of LLM calls. The System 1 Agents framework is freely available as open-source software at https://github.com/eltzanis/SystemOneAgents.

Figures & tables

Explore similar work

CardsList
  1. Context Is a Pipeline, Not a Window: Information Attrition in LLM Agent Harnesses

    Oct 26, 2026Yuvraj Sehgal, Mahsa Panahandeh, Naser Ezzati-JivanLLM Context ManagementLLM Agent Harnesses

  2. How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression

    Oct 7, 2026Xijie Gong, Tingxu Han, Jiahao Zhang +5LLM Tool UseLLM Decision-Making

  3. Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents

    May 21, 2026Asaf Yehudai, Lilach Eden, Michal Shmueli-ScheuerLLM Agent EvaluationAI Agent Benchmarks