The promise of Large Language Model (LLM) agents is to perform complex, stateful tasks. This promise is stunted by significant risks - policy violations, process corruption, and security flaws - that stem from the lack of visibility and mechanisms to manage undesirable data flows produced by agent actions. Today, agent workflows are responsible for enforcing these policies in ad hoc ways. Just as data validation and access controls shifted from the application to the DBMS, freeing application developers from these concerns, we argue that systems should support Data Flow Controls (DFCs) and enforce DFC policies natively. This paper describes early work developing a portable instance of DFC for DBMSes and outlines a broader research agenda toward DFC for agent ecosystems.
翻译：大型语言模型（LLM）智能体的核心价值在于执行复杂且具有状态保持能力的任务。然而，这一潜力因重大风险而受限——包括策略违规、流程腐化及安全漏洞——这些风险源于智能体行为产生的不良数据流缺乏可见性与管理机制。当前，智能体工作流仅能以临时方式负责执行这些策略。正如数据验证与访问控制从应用程序层转移至数据库管理系统（DBMS），使应用开发者得以摆脱这些负担，我们认为系统应当原生支持数据流控制（DFCs）并强制执行DFC策略。本文阐述了为DBMS开发可移植DFC实例的早期工作，并勾勒了面向智能体生态系统的DFC更广泛研究路线图。
相关内容
微信扫码咨询专知VIP会员