EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913939101581312 |
|---|---|
| author | Zhu, Chenglin Zhang, Tao Li, Chong Lin, Mingan Zhou, Zenan Xie, Jian |
| author_facet | Zhu, Chenglin Zhang, Tao Li, Chong Lin, Mingan Zhou, Zenan Xie, Jian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09374 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique Zhu, Chenglin Zhang, Tao Li, Chong Lin, Mingan Zhou, Zenan Xie, Jian Artificial Intelligence I.2.6; I.2.10 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. |
| title | EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique |
| topic | Artificial Intelligence I.2.6; I.2.10 |
| url | https://arxiv.org/abs/2507.09374 |