# Progressive Multimodal Reasoning via Active Retrieval arXiv: https://arxiv.org/abs/2412.14835 ยท HTML: https://mlsanity.com/paper/2412.14835/ ## Key facts - Cited by 25 papers in the map (data through 14 Oct 2026). - Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. - Builds on 7 of its 127 references that are in the map. - First posted on arXiv 19 Dec 2024. ## Placed in - LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/) - Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/) ## Builds on (most cited first, 7 of 7) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024) - [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023) - [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024) - [Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://mlsanity.com/paper/2410.08146/) (2024) - [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024) - [CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery](https://mlsanity.com/paper/2406.08587/) (2024) ## Built on by (most cited first, 25 of 25) - [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025) - [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025) - [Agentic Reinforced Policy Optimization](https://mlsanity.com/paper/2507.19849/) (2025) - [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025) - [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025) - [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025) - [Agentic Entropy-Balanced Policy Optimization](https://mlsanity.com/paper/2510.14545/) (2025) - [ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding](https://mlsanity.com/paper/2501.07861/) (2025) - [Boosting MLLM Reasoning with Text-Debiased Hint-GRPO](https://mlsanity.com/paper/2503.23905/) (2025) - [We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning](https://mlsanity.com/paper/2508.10433/) (2025) - [V-Thinker: Interactive Thinking with Images](https://mlsanity.com/paper/2511.04460/) (2025) - [AStar: Boosting Multimodal Reasoning with Automated Structured Thinking](https://mlsanity.com/paper/2502.02339/) (2025) - [BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning](https://mlsanity.com/paper/2501.03226/) (2025) - [OmniCaptioner: One Captioner to Rule Them All](https://mlsanity.com/paper/2504.07089/) (2025) - [ProgCo: Program Helps Self-Correction of Large Language Models](https://mlsanity.com/paper/2501.01264/) (2025) - [A Survey of Deep Learning for Geometry Problem Solving](https://mlsanity.com/paper/2507.11936/) (2025) - [EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique](https://mlsanity.com/paper/2507.09374/) (2025) - [Empowering Multimodal LLMs with External Tools: A Comprehensive Survey](https://mlsanity.com/paper/2508.10955/) (2025) - [DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training](https://mlsanity.com/paper/2509.05542/) (2025) - [From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models](https://mlsanity.com/paper/2511.12861/) (2025) - [Towards Understanding Multimodal Fine-Tuning: Spatial Features](https://mlsanity.com/paper/2602.08713/) (2026) - [Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.17354/) (2025) - [Pseudocode-Guided Structured Reasoning for Automating Reliable Inference in Vision-Language Models](https://mlsanity.com/paper/2605.19663/) (2026) - [The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes](https://mlsanity.com/paper/2606.11470/) (2026) - [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026) ## Abstract (arXiv) 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 this paper, we propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs through Active Retrieval (AR) and Monte Carlo Tree Search (MCTS). Our approach begins with the development of a unified retrieval module that retrieves key supporting insights for solving complex reasoning problems from a hybrid-modal retrieval corpus. To bridge the gap in automated multimodal reasoning verification, we employ the MCTS algorithm combined with an active retrieval mechanism, which enables the automatic generation of step-wise annotations. This strategy dynamically retrieves key insights for each reasoning step, moving beyond traditional beam search sampling to improve the diversity and reliability of the reasoning space. Additionally, we introduce a process reward model that aligns progressively to support the automatic verification of multimodal reasoning tasks. Experimental results across three complex multimodal reasoning benchmarks confirm the effectiveness of the AR-MCTS framework in enhancing the performance of various multimodal models. Further analysis demonstrates that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.