Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Anthropic Fellows researchers tested frontier models from Anthropic, OpenAI and Alibaba in four simulated multi-user settings. In each, one coordinating agent beat a team of per-user agents. In the shared API-budget task, fewer agents acted as teams grew, and GPT and Qwen agents cancelled others' jobs without asking. In group orders, agents often checked out before reading all messages. A team lead helped with budgets, while a checkout guard recovered 62–73% of failed Claude orders.