Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911136862961664 |
|---|---|
| author | Bentley, Peter J. Lim, Soo Ling Ishikawa, Fuyuki |
| author_facet | Bentley, Peter J. Lim, Soo Ling Ishikawa, Fuyuki |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03380 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems Bentley, Peter J. Lim, Soo Ling Ishikawa, Fuyuki Artificial Intelligence Computation and Language 93A16 I.2.11 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. |
| title | Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems |
| topic | Artificial Intelligence Computation and Language 93A16 I.2.11 |
| url | https://arxiv.org/abs/2509.03380 |