让多模态大模型像人一样一步步思考并反思，提升解题能力。
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
- 用多模型协作的蒙特卡洛树搜索，逐步探索推理路径。
- 构建26万条带完整推理链的数据集，支持模型持续学习。
- 适合需要深度推理的多模态任务，如复杂视觉问答。
本文旨在开发一种多模态大模型（MLLM），通过学习生成每个推理步骤直至最终答案来理解与解答问题。为此，我们提出集体蒙特卡洛树搜索（CoMCTS），一种用于MLLM的新型学习推理方法，将集体学习引入树搜索，以高效、有效地寻找和学习有效推理路径。CoMCTS的核心思想是利用多个模型的集体知识，通过四步迭代操作——扩展、模拟与错误定位、反向传播、选择——协同推测、搜索并识别通往正确答案的有效推理路径。基于CoMCTS，我们构建了包含26万条问题的多模态数据集Mulberry-260k，每条问题均带有丰富、明确且结构化的推理节点树。利用该数据集，我们进行集体监督微调（SFT），训练出具备o1类逐步推理与反思能力的多模态大模型——Mulberry。大量实验表明，所提方法在多个基准测试中表现优越。代码将公开于https://github.com/HJYao00/Mulberry。
原文摘要 · Abstract (English)
In this work, we aim to develop an MLLM that understands and solves questions by learning to create each intermediate step of the reasoning involved till the final answer. To this end, we propose Collective Monte Carlo Tree Search (CoMCTS), a new learning-to-reason method for MLLMs, which introduces the concept of collective learning into ``tree search'' for effective and efficient reasoning-path searching and learning. The core idea of CoMCTS is to leverage collective knowledge from multiple models to collaboratively conjecture, search and identify effective reasoning paths toward correct answers via four iterative operations including Expansion, Simulation and Error Positioning, Backpropagation, and Selection. Using CoMCTS, we construct Mulberry-260k, a multimodal dataset with a tree of rich, explicit and well-defined reasoning nodes for each question. With Mulberry-260k, we perform collective SFT to train our model, Mulberry, a series of MLLMs with o1-like step-by-step Reasoning and Reflection capabilities. Extensive experiments demonstrate the superiority of our proposed methods on various benchmarks. Code will be available at https://github.com/HJYao00/Mulberry
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。