| Challenge: | Existing approaches to deploying large multimodal models rely on rigid pipelines . Existing methods such as retrieval-augmented generation and prompt engineered search rely only on rigid knowledge sources. |
| Approach: | They propose a framework that enables LMMs to perform on-demand, multi-turn search in real-world Internet environments. |
| Outcome: | The proposed model outperforms existing models while reducing search calls by over 30%. |
Similar Papers
End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MM-RAG is a promising approach for enhancing the reliability and factuality of large vision-language models . current methods focus on component-level optimizations and necessitate extensive component-specific training datasets . |
| Approach: | They propose a new paradigm that backpropagates global rewards to each component . this backpropage transforms local losses into specific local losses . |
| Outcome: | The proposed paradigm achieves high training efficiency on knowledge-intensive multimodal benchmarks. |
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query. |
| Approach: | They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis. |
| Outcome: | The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO. |
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A (2026.acl-industry)
Copied to clipboard
Hanoz Bhathena, Parin Rajesh Jhaveri, Rohan Mittal, Prateek Singh, Aymen Kallala, Rachneet Kaur, Yiqiao Jin, Zhen Zeng, Adwait Ratnaparkhi, Denis Kochedykov
| Challenge: | Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and answer generation. |
| Approach: | They propose a document structure-aware split that extracts and represents document structure via a structure-based split that dynamically routes documents through orientation-specific ingestion pipelines. |
| Outcome: | The proposed model outperforms state-of-the-art vision-centric baselines by up to 32% points and achieves strong gains on report-style layouts. |
DORA: A Dual-Objective Reinforcement Learning Framework for Effective and Efficient Multimodal Agentic Search (2026.acl-long)
Copied to clipboard
Guangming Qin, Yuhao Deng, Yukun Zhao, Zhenyang Li, Junfeng Wang, Dawei Yin, Ye Yuan, Guoren Wang, Yizhou Yan, Chengliang Chai, Lei Cao
| Challenge: | Existing methods to train large language models overlook quality of intermediate search results . existing methods often invoke search calls during reasoning, making inference inefficient . |
| Approach: | They propose a dual-objective reinforcement learning framework to improve search strategies of MLLMs . DORA outperforms state-of-the-art methods, achieving up to 8.4% higher accuracy . |
| Outcome: | The proposed model outperforms state-of-the-art methods while reducing search calls by 9.7%. |
s3: You Don’t Need That Much Data to Train a Search Agent via RL (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to optimize retrieval using search-only metrics ignore downstream utility and fine-tune entire LLM to jointly reason and retrieve limit retrieval utility and compatibility with frozen or proprietary models. |
| Approach: | They propose a lightweight, model-agnostic framework that decouples the searcher from the generator and trains the search user using a Gain Beyond RAG reward. |
| Outcome: | The proposed framework outperforms baselines trained on over 70 more data with 2.4k training samples. |
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
Mohammad Mahdi Abootorabi, Amirhosein Zobeiri, Mahdi Dehghani, Mohammadali Mohammadkhani, Bardia Mohammadi, Omid Ghahroodi, Mahdieh Soleymani Baghshah, Ehsaneddin Asgari
| Challenge: | Large Language Models (LLMs) suffer from hallucinations and outdated knowledge due to their reliance on static training data. |
| Approach: | They review training strategies, robustness enhancements, loss functions, and agent-based approaches and outline open challenges and future directions to guide research in this evolving field. |
| Outcome: | The proposed model improves accuracy and accuracy while integrating external dynamic information for improved factual grounding. |
Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing search-augmented approaches rely on indiscriminate whole-image retrieval and lack deep iterative reflection, limiting their effectiveness on complex visual queries. |
| Approach: | They propose a fully autonomous framework that shifts from passive perception to active visual planning and introduces a Selective Gaze mechanism that dynamically chooses whether to glance at global context or gaze into high-value regions. |
| Outcome: | Experiments across six benchmarks demonstrate state-of-the-art performance. |
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Jingbo Sun, Wenyue Chong, Songjun Tu, Qichao Zhang, Yaocheng Zhang, Jiajun Chai, Xiaohan Wang, Wei Lin, Guojun Yin, Dongbin Zhao
| Challenge: | Prior work limits search depth to reduce cost, but this often leads to underexploration of complex questions. |
| Approach: | They propose a reinforcement learning framework that evaluates each search step via self-generated intermediate answers. |
| Outcome: | Extensive experiments on multiple benchmarks show that AutoSearch achieves a superior accuracy-efficiency trade-off, alleviating over-searching while preserving search quality. |
REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark (2025.acl-long)
Copied to clipboard
Navve Wasserman, Roi Pony, Oshri Naparstek, Adi Raz Goldfarb, Eli Schwartz, Udi Barzelay, Leonid Karlinsky
| Challenge: | Existing benchmarks do not fully capture real-world retrieval challenges . existing benchmarks lack a complete understanding of how models perform in realistic setups . |
| Approach: | They propose an automatic benchmark to address four key properties essential for real-world retrieval: (i) multi-modal documents, (ii) enhanced difficulty, ( (iv) Realistic-RAG queries and (v) accurate labeling. |
| Outcome: | The proposed model reveals significant model weaknesses, particularly in handling table-heavy documents and robustness to query rephrasing. |
MDocRAG-RL: Empowering Multi-Modal Document RAG via Complex Visual Reasoning with Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing RAG systems produce suboptimal embeddings and naively insert images into context without adequate visual perception, limiting reasoning capabilities. |
| Approach: | They propose a novel RAG framework for complex visual reasoning that integrates multimodal large language models with external knowledge to enhance retrieval efficiency. |
| Outcome: | The proposed framework achieves state-of-the-art performance on multiple benchmarks. |