Anthropic releases MAMUBench: single coordinating agent outperforms per-user agent teams across four environments
Original title:Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams
AI summary
An Anthropic Fellows Program team built four multi-user multi-agent simulated environments (shared API token budget, clinic calendar, group food or travel booking, and merged queues), tested frontier models from Anthropic, OpenAI and Alibaba, and released three of the environments as the MAMUBench benchmark.
Key Takeaways
- An Anthropic Fellows Program team built four multi-user multi-agent simulated environments (shared…
- clinic calendar,group food or travel booking
- and merged queues),tested frontier models from Anthropic,OpenAI and Alibaba,and released three of…
Quick Facts
- Published
- Updated
- Category
- Papers & Research
- AI score
- 70
Anthropic 用四个模拟环境测出多用户多智能体团队的协调失败模式,并发布 MAMUBench 供社区复测。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Anthropic releases MAMUBench: single coordinating agent outperforms per-user agent teams across four environments. November 11, 2026. https://new.nat6.net/en/news/z9u4n1e7zfapxjozcn97quhdp/