paper-with-me

Papers

Progressive Multimodal Reasoning via Active Retrieval

2024-12-19 · Guanting Dong, Chenghao Zhang, Mengjie Deng, Yutao Zhu, Zhicheng Dou, Ji-Rong Wen

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.

📄 PDF Abstract BibTeX arXiv:2412.14835

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityMultimodal ReasoningRetrieval

Similar Papers 제목 키워드 기반

Hybrid Retriever Evolution for Multimodal Document Reasoning Agents

2026-06-28 · Bohan Yao, Shruthan Radhakrishna, Vikas Yadav arxiv

Different retrievers, including lexical, semantic, and multimodal approaches, provide highly complementary strengths for multimodal document understanding, yet most systems combine them through fixed pipelines that canno…

Question Answering

Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering

2025-08-31 · Changin Choi, Wonseok Lee, Jungmin Ko, Wonjong Rhee arxiv

Knowledge-intensive visual question answering (VQA) requires external knowledge beyond image content, demanding precise visual grounding and coherent integration of visual and textual information. Although multimodal ret…

Visual Question AnsweringVisual Grounding

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

2026-02-05 · Dongyang Chen, Chaoyang Wang, Dezhao Su, Xi Xiao 외 arxiv

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely lang…

Reinforcement Learning

Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models

2025-10-21 · Lehan Wang, Yi Qin, Honglong Yang, Xiaomeng Li arxiv

Incentivizing the reasoning ability of Multimodal Large Language Models (MLLMs) is essential for medical applications to transparently analyze medical scans and provide reliable diagnosis. However, existing medical MLLMs…

Reinforcement Learning

PLUME: Latent Reasoning Based Universal Multimodal Embedding

2026-04-02 · Chenwei He, Xiangzhao Hao, Tianyu Yang, Yuxiang Ma 외 arxiv

Universal multimodal embedding (UME) maps heterogeneous inputs into a shared retrieval space with a single model. Recent approaches improve UME by generating explicit chain-of-thought (CoT) rationales before extracting e…