mlsanityData to 7 Oct 2026

MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline

arXiv 2603.01050 ↗First posted 1 Mar 2026cs.CV cs.AIcited by 18

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

We aim to develop a multimodal research agent capable of explicit reasoning and planning, multi-tool invocation, and cross-modal information synthesis, enabling it to conduct deep research tasks. However, we observe three main challenges in developing such agents: (1) scarcity of search-intensive multimodal QA data, (2) lack of effective search trajectories, and (3) prohibitive cost of training with online search APIs. To tackle them, we first propose Hyper-Search, a hypergraph-based QA generation method that models and connects visual and textual nodes within and across modalities, enabling to generate search-intensive multimodal QA pairs that require invoking various search tools to solve. Second, we introduce DR-TTS, which first decomposes search-involved tasks into several categories according to search tool types, and respectively optimize specialized search tool experts for each tool. It then recomposes tool experts to jointly explore search trajectories via tree search, producing trajectories that successfully solve complex tasks using various search tools. Third, we build an offline search engine supporting multiple search tools, enabling agentic reinforcement learning without using costly online search APIs. With the three designs, we develop MM-DeepResearch, a powerful multimodal deep research agent, and extensive results shows its superiority across benchmarks. Code is available at https://github.com/HJYao00/MM-DeepResearch

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 51 of its 55 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

51 of 55 references.

Closest ancestors · 6

Same direction, newest first

  1. 2026DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation14 Jan
  2. 2025MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling14 Nov
  3. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs13 Jul
  4. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents23 Jun
  5. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges12 Jun
  6. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan

Other references · 45

  1. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  2. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  3. 2025Qwen3-VL Technical Reportcited by 2,534
  4. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  5. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  6. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  7. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  8. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 653
  9. 2025Kimi K2: Open Agentic Intelligencecited by 523
  10. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 439
  11. 2025Seed1.5-VL Technical Reportcited by 367
  12. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 296
33 more
  1. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  2. 2023Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?cited by 203
  3. 2016FVQA: Fact-based Visual Question Answeringcited by 181
  4. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 171
  5. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 165
  6. 2026MiMo-V2-Flash Technical Reportcited by 163
  7. 2025MMSearch-R1: Incentivizing LMMs to Searchcited by 120
  8. 2025DeepEyesV2: Toward Agentic Multimodal Modelcited by 119
  9. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 114
  10. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Toolscited by 106
  11. 2024MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Enginescited by 98
  12. 2025jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrievalcited by 72
  13. 2025PyVision: Agentic Vision with Dynamic Toolingcited by 71
  14. 2025VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learningcited by 68
  15. 2025SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Modelscited by 61
  16. 2025rStar2-Agent: Agentic Reasoning Technical Reportcited by 54
  17. 2025Visual Agentic Reinforcement Fine-Tuningcited by 53
  18. 2025R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPOcited by 52
  19. 2025Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decodingcited by 52
  20. 2024MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Trainingcited by 50
  21. 2024Dense Connector for MLLMscited by 48
  22. 2025DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Searchcited by 41
  23. 2025MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agentscited by 39
  24. 2026LongCat-Flash-Thinking-2601 Technical Reportcited by 32
  25. 2025SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learningcited by 31
  26. 2024Improving Retrieval Augmented Language Model with Self-Reasoningcited by 28
  27. 2026STEP3-VL-10B Technical Reportcited by 28
  28. 2025Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Frameworkcited by 20
  29. 2025A Survey on Agentic Multimodal Large Language Modelscited by 19
  30. 2025Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Usecited by 16
  31. 2025MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGIcited by 14
  32. 2025M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generationcited by 7
  33. 2025ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answeringcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 18.

18 papers.

Sort:

By area:

  1. 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agentscited by 18
  2. 2026VisBrowse-Bench: Benchmarking Visual-Native Search for Multimodal Browsing Agentscited by 8
  3. 2026MTA-Agent: An Open Recipe for Multimodal Deep Search Agentscited by 7
  4. 2026H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillationcited by 7
  5. 2026Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoningcited by 5
  6. 2026From Web to Pixels: Bringing Agentic Search into Visual Perceptioncited by 3
  7. 2026S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agentscited by 3
  8. 2026POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Managementcited by 1
  9. 2026Valley3: Scaling Omni Foundation Models for E-commercecited by 1
  10. 2026Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoningcited by 1
  11. 2026Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Searchcited by 1
  12. 2026SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Searchcited by 1
6 more
  1. 2026DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agentscited by 0
  2. 2026Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agentscited by 0
  3. 2026Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Modelscited by 0
  4. 2026EviRover: Reinforcing Agentic Perception Beyond a Glancecited by 0
  5. 2026Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptationcited by 0
  6. 2026OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Videocited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
  2. 2026ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
  3. 2026Towards Long-horizon Agentic Multimodal Search
  4. 2026VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
  5. 2026EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
  6. 2026Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents
  7. 2026SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task
  8. 2026WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents