Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking
Multimodal large language models (MLLMs) exhibit impressive capabilities but still face challenges in complex visual reasoning. While recent efforts attempt to enhance MLLMs' reasoning by incorporating OpenAI o1-like structured thinking through explicit search structures or teacher-guided distillation, they often struggle to balance performance and efficiency. A critical limitation is their heavy reliance on extensive data and search spaces, resulting in low-efficiency implicit insight extraction and data utilization. To address this, we propose AStar, an Automated Structured thinking paradigm for multimodal reasoning via Monte Carlo Tree Search (MCTS). AStar automatically derives high-level cognitive reasoning patterns from limited data using MCTS-powered hierarchical structures. Building on these explicit patterns, we design a unified reasoning framework that seamlessly integrates models' internal reasoning capabilities and external reasoning guidelines, enabling efficient inference with minimal tree iterations. This novel paradigm strikes a compelling balance between performance and efficiency. Extensive experiments demonstrate AStar's effectiveness, achieving superior accuracy (54.0$\%$) on the MathVerse benchmark with a 7B backbone, surpassing GPT-4o (50.2$\%$) while maintaining substantial data and computational efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyMultimodal ReasoningVisual ReasoningSimilar Papers 제목 키워드 기반
Progressive Multimodal Reasoning via Active Retrieval
Multi-step multimodal reasoning tasks pose significant challenges for multimodal large language models (MLLMs), and finding effective ways to enhance their performance in such scenarios remains an unresolved issue. In th…
DiversityMultimodal ReasoningRetrievalTowards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs. Techniques such as SFT or DPO have enabled LLMs to distill high-quality behaviors from MCTS, i…
Mathematical ReasoningPRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require de…
EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique
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…
MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search
We introduce MCTS-RAG, a novel approach that enhances the reasoning capabilities of small language models on knowledge-intensive tasks by leveraging retrieval-augmented generation (RAG) to provide relevant context and Mo…
Decision MakingRAGRetrievalRetrieval-augmented Generation