Multi‐agent systems (MAS) are helping to unleash AI from the solitary confinement of standalone applications so they can perform coordinated actions in the wider world, functioning within distributed networks of people, tools, and other agents. However, there are unique safety issues that emerge when agents move fr...
Jeffrey M. Bradshaw, Nancy J. Cooke, Michael A. Goodrich et al.· The AI Magazine· 1 citation
The needed requirements for making MAS “better together” are outlined and innovative research relating to these requirements is grouped under four headings: enabling scalable teamwork; assuring multi‐agent alignment; managing the nuanced dynamics of trust and delegation; theory and design of “coordination‐first” system...
Jeffrey M. Bradshaw, Nancy J. Cooke, Michael A. Goodrich et al.· The AI Magazine· 1 citation
This paper contrasts Coordination‐First architectures that explicitly address the competencies and constraints of coordinated joint activity across multiple roles and layers with the current Coordination‐Last paradigm that focuses primarily on deploy‐fast‐and‐fix‐later strategies.
David L. Alderson, David D. Woods· The AI Magazine· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.