Get the latest tech news

How RecursiveMAS speeds up multi-agent inference by 2.4x and reduces token usage by 75%

None

Get the Android app

Or read this on Venture Beat

Read more on:

Photo of token usage

token usage

Photo of RecursiveMAS

RecursiveMAS

Related news:

Improving LLM token usage when debugging

« Intercom, now called Fin, launches an AI agent whose only job is managing another AI agent

Exclusive: Hackers have breached tank readers at US gas stations; officials suspect Iran is responsible »