Language-Based Agent Control

Timothy Zhou submitted an arXiv paper on 13 May 2026, revised 15 October 2026, introducing language-based agent control (LBAC), a programming model that requires AI agents to generate programs that are well typed against surrounding scaffolding code so unsafe programs are rejected by the type-checker before execution. LBAC applies policies uniformly across agent-generated behavior and developer-written scaffolding while letting agents perform arbitrary side-effect-free computation and recursively invoke subagents with full tool access under the same or stricter policies. The paper demonstrates the model with three case studies: I/O sandboxing via filesystem capabilities, data provenance, and information-flow control.

Computer Science Programming Languages Submitted on 13 May 2026 v1 https://arxiv.org/abs/2605.12863v1 , last revised 15 Oct 2026 this version, v2 Title:Language-Based Agent Control View PDF https://arxiv.org/pdf/2605.12863 HTML experimental https://arxiv.org/html/2605.12863v2 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. Submission history From: Timothy Zhou view email https://arxiv.org/show-email/a1cd33a3/2605.12863 Wed, 13 May 2026 01:21:05 UTC 82 KB \ v1\ https://arxiv.org/abs/2605.12863v1 v2 Thu, 15 Oct 2026 01:22:09 UTC 92 KB Additional Features Current browse context: cs.PL References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .