iCreatAI News
Skip to content
Hacker News AI· mklont·· 2 hr agoAI score64

System 1 Agents – a method for local, reliable and fast agentic AI

System 1 Agents – a method for local, reliable and fast agentic AI

AI summary

The authors present System 1 agents, which call tools without generating text: a deterministic compiler turns a tool's JSON schema and the user's request into typed multiple-choice questions, and a local decision model answers each with option probabilities in one forward pass, while code assembles the call. Across 157 MCP tools from 18 medical-imaging and biomedical servers, the best System 1 agent made 93.9% of requests fully correct versus 91.3% for the best local LLM agent, with no invented tool, argument or value detected in 10,888 System 1 calls and 86.2–93.7% correct handling of underspecified requests versus 0.0–5.7% for LLM agents. The repository releases code, data, results and figures, with instructions to reproduce the paper's results on CPU and to build agents for other MCP tool catalogues.

Source: Hacker News AI · github.com