# Language-Based Agent Control

arXiv: https://arxiv.org/abs/2605.12863 · HTML: https://mlsanity.com/paper/2605.12863/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 30 references that are in the map.
- First posted on arXiv 13 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 7 of 7)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Securing AI Agents with Information-Flow Control](https://mlsanity.com/paper/2505.23643/) (2025)
- [Contextual Agent Security: A Policy for Every Purpose](https://mlsanity.com/paper/2501.17070/) (2025)
- [An AI Agent Execution Environment to Safeguard User Data](https://mlsanity.com/paper/2604.19657/) (2026)
- [Linear Haskell: practical linearity in a higher-order polymorphic language](https://mlsanity.com/paper/1710.09756/) (2017)
- [Resource-Guided Program Synthesis](https://mlsanity.com/paper/1904.07415/) (2019)
- [Flux: Liquid Types for Rust](https://mlsanity.com/paper/2207.04034/) (2022)

## Built on by (most cited first, 1 of 1)

- [Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents](https://mlsanity.com/paper/2607.23586/) (2026)

## Abstract (arXiv)

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.