让AI agent主动感知环境变化，实现零信息泄露。
Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems
- 基于环境变化触发行为，构建动态感知框架
- 相比传统架构83%信息泄露，实现零泄露
- 适合对安全与效率要求高的智能系统
当前的代理型大模型AI常沦为自主聊天机器人：遵循脚本运行，受不可靠指挥者控制。本文提出一种自下而上的框架，将AI代理置于其环境中，所有行为均由环境变化触发。引入‘方面’（aspects）概念，类似生物的‘环境感知域’（umwelt），使不同代理以不同方式感知环境，从而更清晰地控制信息流。我们提供一个演示实现，表明相较于典型架构高达83%的信息泄露率，该方法可实现零信息泄露。我们预期，专业代理在各自信息生态位中高效协作的思路，能显著提升系统的安全性和效率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。