---
format: "aidr-story-markdown/v1"
id: "f87e14ef06b6e708ed2ec4dc1cf5561507442e867a0745a56aedc9a255b2cc3c"
canonical_url: "https://aidr.today/f87e14ef?lang=en"
title: "Patterns and problems in emerging multi-agent systems"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-08-16T02:12:53.000Z"
category: "Agents"
topics: ["anthropic","claude","multi-agent","agent","safety","research"]
source_urls: ["https://www.anthropic.com/research/multiagent-systems"]
summary: "We ran experiments on swarms of Claude agents and found coordination failures, collusion, and sabotage. Here, we share what they mean for AI safety."
---

# Patterns and problems in emerging multi\-agent systems

> [Open the canonical story](<https://aidr.today/f87e14ef?lang=en>)

**Published:** 2026-08-16T02:12:53.000Z
**Category:** Agents
**Topics:** anthropic, claude, multi\-agent, agent, safety, research

## Summary

We ran experiments on swarms of Claude agents and found coordination failures, collusion, and sabotage\. Here, we share what they mean for AI safety\.

## Sources

- [Story source](<https://www.anthropic.com/research/multiagent-systems>)