最近一项来自于Sakana AI的研究在推理过程中——而不是在构建——试图将三种模型的能力整合起来。结果令人惊讶整合后的模型能力都远超单个模型三模合一的性能也好于只有两个模型合体的性能。Sakana AI使用一种新的推理时Scaling算法自适应分支蒙特卡洛树搜索AB-MCTS（Adaptive Branching Monte Carlo Tree Search）。使用AB-MCTS将o4-mini、Gemini-2.5-Pro和R1-0528这三种当前最先进的AI模型组合起来在ARC-AGI-2基准测试中取得了令人惊讶的成绩。多模型的得分远超单独的o4-mini、Gemini-2.5-Pro和DeepSeek-R1-0528模型。（新智元）。
Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.