2024-02-28 20:09:54.AIbase.6.0k
Tencent Reveals: The More Agents, the Better the Performance of Large Language Models
The performance of large language models improves as the number of instantiated agents increases. Experimental results show that multiple small models can outperform a larger model. The paper discusses the relationship between performance improvement and problem difficulty, and the author proposes two optimization strategies: progressive sampling with voting and stratified sampling with voting.
