More Agents Is All You Need
This addresses the need for scalable and orthogonal methods to boost LLM performance, though it appears incremental as it builds on existing agent-based approaches.
The paper tackles the problem of enhancing large language model (LLM) performance by showing that a simple sampling-and-voting method, called Agent Forest, scales with the number of agents, with improvements correlated to task difficulty, achieving gains across various benchmarks.
We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated. Also, this method, termed as Agent Forest, is orthogonal to existing complicated methods to further enhance LLMs, while the degree of enhancement is correlated to the task difficulty. We conduct comprehensive experiments on a wide range of LLM benchmarks to verify the presence of our finding, and to study the properties that can facilitate its occurrence. Our code is publicly available at: https://github.com/MoreAgentsIsAllYouNeed/AgentForest