Bespoke Labs releases Multi Agent Coordination Bench: 12 multi-agent tasks show poor coordination

AlexGDimakis · x · 2026-11-19

Bespoke Labs released the Multi Agent Coordination Bench, twelve natively multi-agent long-horizon tasks measuring coordination, collaboration and communication of frontier models. Key finding: multi-agent systems often behave like a mob rather than a coordinated team — eight agents beat a single agent, but mostly thanks to parallel random exploration, with genuinely poor coordination and communication.

Original post →

More from coding & agent

coding & agent channel →