AI agents can carry out complex tasks autonomously. Getting them to work together usually relies on speaking to each other, typically in English.
This creates considerable computational overhead, which grows rapidly if agents engage in a repeated back-and-forth communication.
Researchers from Microsoft have developed a new method named ‘Droidspeak’ that communicates 2.78 times faster with little accuracy lost.
Professor Philip Feldman at the University of Maryland, believes that the resulting communication speed-ups could help multi-agent systems tackle bigger, more complex problems than currently possible using natural language.
MORE