Papers & Research

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
Source
Anthropic:Alignment Science Blog(网页)
Category
Papers & Research
Topic
AgentAnthropic / ClaudeSafety & Alignment
AI score
70
Read the original Read the full article at the original source
Why it matters

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。

Topics

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.

Original article · AIHOT entry

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/

View all →