Sakana AI’s TreeQuest: Deploy Multi-Model Teams that Outperform Individual LLMs by 30%

Sakana AI’s TreeQuest: Deploy multi-model teams that outperform individual LLMs by 30%

Sakana AI's new inference-time scaling technique uses Monte-Carlo Tree Search to orchestrate multiple LLMs to collaborate on complex tasks.

Sakana AI’s New Algorithm Can Let Gemini and ChatGPT Work Together

Sakana AI released an open-source algorithm on Tuesday, which allows multiple artificial intelligence (AI) models to collaborate on complex problems. Dubbed Adaptive Branching Monte Carlo Tree Search (AB-MCTS), it is an inference-time scaling or test-time scaling algorithm that adds a third dimension to the existing framework of large language models (LLMs).