Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Turn: A Language for Agentic Computation

Muyukani Kizito

TL;DR

Turn is presented, 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).

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 model}, derived from Erlang, gives each agent an isolated context window, persistent memory, and mailbox. A \emph{capability-based identity system} returns opaque, unforgeable handles from the VM host, ensuring raw credentials never enter agent memory. Finally, \emph{compile-time schema absorption} (\texttt{use schema::<protocol>}) synthesizes typed API bindings from external specifications at compile time; the \texttt{openapi} adapter is shipped with \texttt{graphql}, \texttt{fhir}, and \texttt{mcp} in active development. We describe the language design, type rules, schema semantics, and a Rust-based bytecode VM, and evaluate Turn against representative agentic workloads. Turn is open source at https://github.com/ekizito96/Turn.

Turn: A Language for Agentic Computation

TL;DR

Turn is presented, 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).

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 model}, derived from Erlang, gives each agent an isolated context window, persistent memory, and mailbox. A \emph{capability-based identity system} returns opaque, unforgeable handles from the VM host, ensuring raw credentials never enter agent memory. Finally, \emph{compile-time schema absorption} (\texttt{use schema::<protocol>}) synthesizes typed API bindings from external specifications at compile time; the \texttt{openapi} adapter is shipped with \texttt{graphql}, \texttt{fhir}, and \texttt{mcp} in active development. We describe the language design, type rules, schema semantics, and a Rust-based bytecode VM, and evaluate Turn against representative agentic workloads. Turn is open source at https://github.com/ekizito96/Turn.
Paper Structure (72 sections, 15 equations, 2 figures, 6 tables)

This paper contains 72 sections, 15 equations, 2 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Paper structure.
  3. Contributions
  4. Running example.
  5. Background and Related Work
  6. Agent Frameworks
  7. Programming Language Theory
  8. Actor model.
  9. Capability-based security.
  10. Session types and structured communication.
  11. Orthogonal persistence.
  12. Attention and Context in LLMs
  13. Agent Identity and Security
  14. Structured LLM Output
  15. Language Design
  16. ...and 57 more sections

Figures (2)

  • Figure 1: Cognitive Type Safety pipeline. A struct definition compiles to a JSON Schema $\mathcal{S}(T)$; the VM embeds it in the inference request, validates the response, and binds a typed value $T$ (Theorem \ref{['thm:conformance']}).
  • Figure 2: Turn compilation pipeline. Macro expansion (use schema) occurs prior to semantic analysis to ensure type resolution.

Theorems & Definitions (4)

  • Definition 1: Inference Expression
  • Definition 2: Confidence Operator
  • Definition 3: Agent Process
  • Definition 4: Identity Capability