# CogPlanner: Unveiling the Potential of Agentic Multimodal Retrieval Augmented Generation with Planning

arXiv: https://arxiv.org/abs/2501.15470 · HTML: https://mlsanity.com/paper/2501.15470/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 26 Jan 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)
- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Visual Question Answering: A Survey of Methods and Datasets](https://mlsanity.com/paper/1607.05910/) (2016)
- [Retrieval Augmented Visual Question Answering with Outside Knowledge](https://mlsanity.com/paper/2210.03809/) (2022)
- [Learning Dense Representations of Phrases at Scale](https://mlsanity.com/paper/2012.12624/) (2020)
- [MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models](https://mlsanity.com/paper/2410.08182/) (2024)
- [RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training](https://mlsanity.com/paper/2303.00534/) (2023)
- [Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications](https://mlsanity.com/paper/2410.21943/) (2024)
- [mR2AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA](https://mlsanity.com/paper/2411.15041/) (2024)

## Built on by (most cited first, 4 of 4)

- [Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.08826/) (2025)
- [A Survey of Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08748/) (2025)
- [Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch](https://mlsanity.com/paper/2512.02395/) (2025)
- [Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering](https://mlsanity.com/paper/2605.27164/) (2026)

## Abstract (arXiv)

Multimodal Retrieval Augmented Generation (MRAG) systems have shown promise in enhancing the generation capabilities of multimodal large language models (MLLMs). However, existing MRAG frameworks primarily adhere to rigid, single-step retrieval strategies that fail to address real-world challenges of information acquisition and query reformulation. In this work, we introduce the task of Multimodal Retrieval Augmented Generation Planning (MRAG Planning) that aims at effective information seeking and integration while minimizing computational overhead. Specifically, we propose CogPlanner, an agentic plug-and-play framework inspired by human cognitive processes, which iteratively determines query reformulation and retrieval strategies to generate accurate and contextually relevant responses. CogPlanner supports parallel and sequential modeling paradigms. Furthermore, we introduce CogBench, a new benchmark designed to rigorously evaluate the MRAG Planning task and facilitate lightweight CogPlanner integration with resource-efficient MLLMs, such as Qwen2-VL-7B-Cog. Experimental results demonstrate that CogPlanner significantly outperforms existing MRAG baselines, offering improvements in both accuracy and efficiency with minimal additional computational costs.