# M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation

arXiv: https://arxiv.org/abs/2508.06328 · HTML: https://mlsanity.com/paper/2508.06328/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 28 of 28)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.06503/) (2022)
- [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://mlsanity.com/paper/2503.07536/) (2025)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models](https://mlsanity.com/paper/2403.12881/) (2024)
- [MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval](https://mlsanity.com/paper/2412.14475/) (2024)
- [MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer](https://mlsanity.com/paper/2401.10208/) (2024)
- [VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2505.22019/) (2025)
- [Visual Agentic Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.14246/) (2025)
- [Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2504.21277/) (2025)
- [A Survey of Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08748/) (2025)
- [Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment](https://mlsanity.com/paper/2411.17188/) (2024)
- [Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines](https://mlsanity.com/paper/2411.16365/) (2024)
- [MuRAR: A Simple and Effective Multimodal Retrieval and Answer Refinement Framework for Multimodal Question Answering](https://mlsanity.com/paper/2408.08521/) (2024)
- [FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion](https://mlsanity.com/paper/2410.12564/) (2024)

## Built on by (most cited first, 7 of 7)

- [Gen-Searcher: Reinforcing Agentic Search for Image Generation](https://mlsanity.com/paper/2603.28767/) (2026)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline](https://mlsanity.com/paper/2603.01050/) (2026)
- [LensWalk: Agentic Video Understanding by Planning How You See in Videos](https://mlsanity.com/paper/2603.24558/) (2026)
- [Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding](https://mlsanity.com/paper/2603.13366/) (2026)
- [Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding](https://mlsanity.com/paper/2510.15253/) (2025)
- [Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI](https://mlsanity.com/paper/2510.16720/) (2025)

## Abstract (arXiv)

Current research on Multimodal Retrieval-Augmented Generation (MRAG) enables diverse multimodal inputs but remains limited to single-modality outputs, restricting expressive capacity and practical utility. In contrast, real-world applications often demand both multimodal inputs and multimodal outputs for effective communication and grounded reasoning. Motivated by the recent success of Reinforcement Learning (RL) in complex reasoning tasks for Large Language Models (LLMs), we adopt RL as a principled and effective paradigm to address the multi-step, outcome-driven challenges inherent in multimodal output generation. Here, we introduce M2IO-R1, a novel framework for Multimodal Retrieval-Augmented Multimodal Generation (MRAMG) that supports both multimodal inputs and outputs. Central to our framework is an RL-based inserter, Inserter-R1-3B, trained with Group Relative Policy Optimization to guide image selection and placement in a controllable and semantically aligned manner. Empirical results show that our lightweight 3B inserter achieves strong reasoning capabilities with significantly reduced latency, outperforming baselines in both quality and efficiency.