Turn: A Language for Agentic Computation
Muyukani Kizito

TL;DR
Turn is a novel programming language designed for autonomous agentic software, integrating language model inference as a core typed primitive with constructs for safety, control, and schema integration.
Contribution
It introduces five language-level constructs that embed LLM inference safety and control directly into the language, unlike prior approaches that treat them as application-level conventions.
Findings
Turn enables typed LLM inference validation.
It provides deterministic control flow based on model confidence.
The language supports schema absorption for API bindings.
Abstract
We present \textbf{Turn}, a compiled, actor-based programming language -- statically typed for schema inference, dynamically typed at the value level -- for agentic software: programs that reason and act autonomously by delegating inference to large language models (LLMs). Existing approaches augment general-purpose languages with frameworks, encoding critical invariants (bounded context, typed inference output, credential isolation, durable state) as application-level conventions rather than language guarantees. Turn introduces five language-level constructs that address this gap. \emph{Cognitive Type Safety} makes LLM inference a typed primitive: the compiler generates a JSON Schema from a struct definition and the VM validates model output before binding. The \emph{confidence operator} enables deterministic control flow gated on model certainty. Turn's \emph{actor-based process…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Model-Driven Software Engineering Techniques · Scientific Computing and Data Management
