Value-Preserving Architectures for Agentic AI Systems
This paper argues that architectural choices influence not only the functionality and performance of MAS but can also promote value-oriented system behavior, laying the foundation for a unified set of architectural patterns and guidelines towards the design of trustworthy MAS.
A. Pesare, Tommaso Dolci, Katja Hose et al.
· Proceedings of the 1st Inter... · 0 citations