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

> Source: <https://discuss.huggingface.co/t/system-1-agents-a-method-for-local-reliable-and-fast-agentic-ai/192267#post_1>
> Published: 2026-11-21 10:41:20+00:00

**Recommendation:** Replace free-text tool selection with a deterministic compiler that turns requests and schemas into multiple-choice questions, so the agent cannot invent values or fabricate missing parameters.
More in the playbook "Designing agent systems": <https://wpnews.pro/playbooks/agent-architecture>

Hey all, we just released a methodology to develop local, reliable and fast System 1 agents!

What if an AI agent could call tools without writing a single word?

Our new preprint introduces System 1 agents: local AI agents that cannot hallucinate by design, because they never generate text. A deterministic compiler turns each request and the tool’s schema into multiple-choice questions, and a decision model answers them by choosing among options that come only from the request, the schema and the tool catalogue.

We developed six System 1 agents and compared them with nine LLM-based agents on 1,952 requests to 157 medical imaging and biomedical tools from 18 MCP servers:

→ 97.0% correct tool choice, significantly ahead of all local LLM-agent settings

→ Zero invented values in 10,888 calls, against 5.5–19.7% of LLM-agent calls

→ Missing information? It asks the user. LLM agents made it up in up to 62.1% of such requests

→ More accurate and cheaper: 92.9% fully correct at 2.6 s and 0.228 Wh per correct request, against 91.3%, 4.5 s and 0.413 Wh for the best LLM agent

→ Everything runs on one local GPU, so sensitive data never leave the institution

 Paper page: [Paper page - System 1 agents: a method for local, reliable and fast agentic AI](https://huggingface.co/papers/2611.21053)

 Code and data: [GitHub - eltzanis/SystemOneAgents: A method to develop System 1 Agents · GitHub](https://github.com/eltzanis/SystemOneAgents)

Feedback and questions are very welcome!
