#AGI 日本 Sakana AI 推出 TreeQuest，一種創新框架讓多個大型語言模型（LLMs）協作解題，整體表現比單一模型高出 30%。他們的 Multi-LLM AB-MCTS 演算法結合多模型推理策略，能根據任務自動選擇最合適的模型，實現真正的 AI「夢幻團隊」。TreeQuest 已開源，為企業提供更強、可組合的 AI 系統。
Japan’s Sakana AI has unveiled TreeQuest, an open-source framework where multiple large language models collaborate to solve complex tasks—outperforming solo LLMs by 30%. Their Multi-LLM AB-MCTS algorithm dynamically assigns sub-tasks to the most suitable model, combining reasoning power and minimizing hallucinations. This could be a game-changer for enterprise-grade AI applications.
📌 一杯咖啡價錢連接 Web3 世界 https://patreon.com/wanszezit
Full article https://venturebeat.com/ai/sakana-ais-treequest-deploy-multi-model-teams-that-outperform-individual-llms-by-30/