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.
More from coding & agent
- 130,000+ SEC Form 144 filings added to a dataset, revealing insider sales up to 4 days before Form 4 — virattt · 2026-11-19
- RadixArk trains DaisyRose-27B in 18 days on 144 H200s, doubling Terminal-Bench score — BanghuaZ · 2026-11-19
- Six deployment strategies compared: rolling, blue-green, canary and more — JeremyCMorgan · 2026-11-19
- New MAC Bench finds frontier agents coordinate poorly: 8-agent teams win by exploration, not teamwork — AlexGDimakis · 2026-11-19
- Dev Argues AI Needs One Interface: Claude or GPT Plus Filesystem or Sandbox — _AustinCalvert_ · 2026-11-19
- 19 Core Concepts of AI System Design: From KV Cache to Multi-Agent Systems — blaizedsouza · 2026-11-19