基于语言的智能体控制（LBAC）：用类型系统约束 AI 智能体行为

View PDF HTML (experimental)

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.

Subjects:	Programming Languages (cs.PL); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
Cite as:	arXiv:2605.12863 [cs.PL]
	(or arXiv:2605.12863v2 [cs.PL] for this version)
	https://doi.org/10.48550/arXiv.2605.12863 arXiv-issued DOI via DataCite

Submission history

From: Timothy Zhou [view email]
[v1] Wed, 13 May 2026 01:21:05 UTC (82 KB)
[v2] Thu, 15 Oct 2026 01:22:09 UTC (92 KB)