将AI智能体置于其所处世界中:面向动态部分可观测信息系统的面向方面智能体AI
Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems
AI总结:
针对现有LLM智能体信息管控弱、泄露率高的问题,提出基于环境触发、引入类umwelt的“方面”概念的自底向上智能体框架,实现零信息泄露,兼顾安全与效率。
摘要:
基于大语言模型(LLM)的智能体AI往往不过是自主聊天机器人:遵循脚本行动,且通常由不可靠的控制器管控。本研究提出一种自底向上的框架,将AI智能体置于其所处环境中,所有行为均由环境变化触发。研究引入了“方面(aspects)”概念,类似于“周遭世界(umwelt)”的理念,即不同智能体集合对环境的感知各不相同,从而实现更清晰的信息管控。我们提供了一个示例性实现,结果表明:典型架构的信息泄露率最高可达83%,而面向方面的智能体AI可实现零信息泄露。我们预期,这种在自身信息生态位中高效工作的专用智能体概念,能够同时提升安全性与效率。
英文摘要:
Agentic LLM AI agents are often little more than autonomous chatbots: actors following scripts, often controlled by an unreliable director. This work introduces a bottom-up framework that situates AI agents in their environment, with all behaviors triggered by changes in their environments. It introduces the notion of aspects, similar to the idea of umwelt, where sets of agents perceive their environment differently to each other, enabling clearer control of information. We provide an illustrative implementation and show that compared to a typical architecture, which leaks up to 83% of the time, aspective agentic AI enables zero information leakage. We anticipate that this concept of specialist agents working efficiently in their own information niches can provide improvements to both security and efficiency.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。