EduFlow：通过多阶段、多视角的评判推进MLLMs的问题解决能力
EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique
AI总结：
针对MLLMs在科学任务多步推理中的不足，提出端到端框架EduFlow，通过EduPRM奖励模型和EduMCTS搜索机制提升教育科学推理的全流程能力，并构建了大规模数据集EduMCTS-160K。
摘要：
多模态大语言模型（MLLMs）在科学任务上表现依然不佳，特别是那些需要多步和可解释推理的任务。其局限性包括科学推理模式不足、多步推理中缺乏全局连贯性以及缺乏反思性自我修正，使其在结构化科学场景中不可靠。我们引入EduFlow，首个覆盖教育科学推理全流程的端到端框架，包括数据选择、基于MCTS的轨迹构建、模型训练和输出优化。其核心是EduPRM，一个过程感知的奖励模型，通过标签和理由评判推理步骤。EduPRM通过课程学习在三种互补监督源上训练：MCTS引导的轨迹、错误注入的评判和师生对话，使其能动态适应多阶段问题解决并在推理时进行迭代优化。我们进一步提出EduMCTS，一个领域适应的搜索框架，引入专为教育推理设计的引导动作，如促进反思性错误纠正的自我反思机制。它进一步利用EduPRM的细粒度反馈引导搜索走向更高质量的推理轨迹。通过应用自一致性和拒绝采样，我们构建了EduMCTS-160K，一个大规模教育推理轨迹数据集。大量实验表明EduFlow增强了推理的一致性和连贯性。代码、数据和模型将发布。
英文摘要：
Multimodal large language models (MLLMs) still perform poorly on scientific tasks, particularly those requiring multi-step and interpretable reasoning. Their limitations include insufficient scientific reasoning patterns, lack of global coherence in multi-step inference, and the absence of reflective self-correction, making them unreliable in structured scientific contexts. We introduce EduFlow, the first end-to-end framework that covers the full pipeline of educational scientific reasoning, including data selection, MCTS-based trajectory construction, model training, and output optimization. At its core is EduPRM, a process-aware reward model that critiques reasoning steps with tags and justifications. EduPRM is trained via curriculum learning on three complementary supervision sources: MCTS-guided trajectories, error-injected critiques, and teacher-student dialogues, enabling dynamic adaptation to multi-stage problem solving and iterative refinement during inference. We further propose EduMCTS, a domain-adapted search framework that introduces bootstrapping actions specifically designed for educational reasoning, such as a self-reflection mechanism that promotes reflective error correction. It further leverages EduPRM's fine-grained feedback to guide the search toward higher-quality reasoning trajectories. By applying self-consistency and rejection sampling, we constructed EduMCTS-160K, a large-scale dataset of educational reasoning trajectories. Extensive experiments demonstrate that EduFlow enhances reasoning consistency and coherence. Code, data, and models will be released.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
