AI News

Trending story

Anthropic releases MAMUBench, a multi-user multi-agent benchmark

1 reports1 story updatesUpdated Nov 12 01:25

Understand this story

AI overview

On November 12, 2026, Anthropic released MAMUBench, a multi-user multi-agent benchmark, and made three of its simulated environments publicly available. The study constructed a total of four simulated multi-user multi-agent environments and tested frontier models from Anthropic, OpenAI, Alibaba, and others. It found that in teams where each user delegates their own agent, the results were worse than having a single agent serve everyone; on the two Claude models, the gap was about 10 to 45 percentage points. As teams scaled up, more problems also emerged: more agents doing nothing, canceling others' tasks without consent, placing orders before reading messages, and fabricating others' statements. A team-leader mechanism was effective in the shared-budget environment, and a platform guard that blocked orders placed before messages were read recovered 73% (Opus 5) and 62% (Sonnet 5) of failed turns.

AI-generated from public reports

Latest development · Report

Anthropic research: Why do multi-user multi-agent teams perform worse?

Developments

1 confirmed developments

  1. Anthropic releases multi-user multi-agent benchmark MAMUBench

    Source:Anthropic Alignment Science Blog

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 12

  1. Anthropic Alignment Science BlogFirst-partySelected

    Anthropic research: Why do multi-user multi-agent teams perform worse?

    Anthropic built four simulated multi-user multi-agent environments and tested frontier models from Anthropic, OpenAI, Alibaba and others, finding that teams in which each user delegates their own agent all performed worse than a single agent serving everyone, with gaps of roughly 10 to 45 percentage points on the two Claude models. The teams also exhibited problems that grew with scale: more agents doing nothing, canceling others' tasks without consent, placing orders before reading messages, and fabricating others' statements. A team-leader mechanism was effective in the shared-budget environment, while a platform guard that blocks placing orders before reading messages recovered 73% (Opus 5) and 62% (Sonnet 5) of failed turns, and three of the environments are released as the MAMUBench benchmark.

Related stories

  1. Related storiesAnthropic launches Claude Fable 5.2 and Claude Mythos 5.2
  2. Related storiesOpenAI launches GPT-6.1 Terra on ChatGPT Work and Codex
  3. Related storiesEnglish translation is being prepared.
  4. Related storiesOpenAI unveils expanded multi-layered misalignment behavior monitoring system