About this paper
A local System 1 agent framework compiles tool schemas and requests into multiple-choice questions answered by a one-pass decision model, enabling accurate biomedical tool calls without text generation or invented content.
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…
agentic artificial intelligencelarge language models (LLMs)local LLMscloud LLMstool callshallucinationSystem 1 agentsdeterministic compilertool schemamultiple-choice questions
- Upvotes
- 6
- Authors
- 2
- Published
- Nov 16, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
System 1 agents: a method for local, reliable and fast agentic AI was first seen on Hugging Face · Daily papers on Nov 21, 2026. Since then it has appeared in 16 checks on 2 different days. Its best position was #29 of 30, reached on Nov 21, 09:29 UTC. It is #30 right now, holding steady at #30 over the last 6 checks.