News for hackers. Stuff that matters.
Re:More Agents Is All You Need: LLMs performance scales with... by xcv123 on Sunday April 07, 2024 @02:49AM (#39958736)
The paper says that it enhances multi-agent methods. It is not a replacement for that. It's an enhancement for existing methods.
Re:More Agents Is All You Need: LLMs performance scales with... by Sharlin on Monday April 08, 2024 @02:50AM (#39966922)
Running the same query several times on the same model and taking the consensus opinion is still a multi-agent method.