Language-Based Agent Control
LBAC is a programming model that enforces user policies on agentic applications by requiring agents to generate well-typed programs rejected by a type-checker before execution.
Published 2026Atlanta Poster Session 5 · Fri, Dec 11, 10:00 AM–1:00 PM local time · Hall C1arXiv ↗OpenReview ↗
Only vote on papers you've read. Sign in with GitHub to vote.
LBAC is a sharp, rigorous framework that binds agent outputs to scaffolding policies via static typing, though it remains untested against adversarial tool abuse, lacks runtime benchmarks, and needs proof that recursive subagent policies compose without…
Abstract
This paper introduces language-based agent control (LBAC), a new programming model for agentic applications that brings techniques from programming languages and language-based security to the problem of agent control. In conventional programming, combinations of static typing and runtime enforcement have long been used to guarantee that well-typed programs satisfy user-specified policies, including policies for access control, information flow, data provenance, and more. The key idea behind LBAC is to extend these guarantees to agentic applications by requiring agents to generate programs that are themselves well typed in the context of the surrounding scaffolding code. Unsafe programs are rejected by the type-checker before execution, allowing policies to apply uniformly across the entire application, including both agent-generated behavior and developer-written scaffolding. At the same time, LBAC preserves substantial expressiveness: agents may perform arbitrary side-effect-free computation and recursively invoke subagents, which retain full tool access subject to the same -- or potentially more restrictive -- policies. We demonstrate LBAC with three case studies: I/O sandboxing via filesystem capabilities, data provenance, and information-flow control.