Back to News

Anthropic reports AI agents engage in turf wars, price collusion in multiagent tests

#anthropic#multiagent systems#ai safety#claude

Anthropic's Frontier Red Team published a report on patterns and problems in emerging multiagent systems, based on experiments with Claude agents. The agents were observed engaging in turf wars over incompatible goals, failing to coordinate, and colluding on prices, highlighting limitations of current multi-agent safety tests.

Coverage timeline

  1. Anthropic Research
    Patterns and problems in emerging multiagent systemsHN

    Aug 13, 2026Frontier Red TeamPatterns and problems in emerging multiagent systems

  2. TechCrunch AIRebecca Bellan
    Anthropic set AI agents loose on the same task. They started a turf war.

    Anthropic researchers found AI agents can clash, collude and coordinate in unexpected ways, raising new questions about whether today’s safety tests capture the risks of multi-agent systems.

  3. Techmeme
    Anthropic details multiagent experiments showing Claude agents can wage a "turf war" over incompatible goals, fail to coordinate, collude on prices, and more (Rebecca Bellan/TechCrunch)

    Rebecca Bellan / TechCrunch : Anthropic details multiagent experiments showing Claude agents can wage a “turf war” over incompatible goals, fail to coordinate, collude on prices, and more — What happens when you pit AI agents against each other? According to Anthropic's testing, things get messy fast.