More Agents Is All You Need: LLMs performance scales with the number of agents 2 years ago
https://anonymous.4open.science/api/repo/more_agent_is_all_y...
How can you have majority voting based on text produced by LLMs, won’t every answer string be essentially distinct with extremely high probability if it’s over a couple dozens bits of output (which any useful LLM output would be, right?)?