mlsanityData to 7 Oct 2026

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

arXiv 2508.05748 ↗First posted 7 Aug 2025cs.IRcited by 114

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Web agents such as Deep Research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains primarily text-centric, overlooking visual information in the real world. This makes multimodal Deep Research highly challenging, as such agents require much stronger reasoning abilities in perception, logic, knowledge, and the use of more sophisticated tools compared to text-based agents. To address this limitation, we introduce WebWatcher, a multi-modal Agent for Deep Research equipped with enhanced visual-language reasoning capabilities. It leverages high-quality synthetic multimodal trajectories for efficient cold start training, utilizes various tools for deep reasoning, and further enhances generalization through reinforcement learning. To better evaluate the capabilities of multimodal agents, we propose BrowseComp-VL, a benchmark with BrowseComp-style that requires complex information retrieval involving both visual and textual information. Experimental results show that WebWatcher significantly outperforms proprietary baseline, RAG workflow and open-source agents in four challenging VQA benchmarks, which paves the way for solving complex multimodal information-seeking tasks.

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 52 of its 59 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

52 of 59 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025PyVision: Agentic Vision with Dynamic Tooling10 Jul
  2. 2024Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent5 Nov

Other references · 50

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  7. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  8. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  9. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  10. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  11. 2023CogAgent: A Visual Language Model for GUI Agentscited by 692
  12. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
38 more
  1. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 494
  2. 2025Humanity's Last Examcited by 467
  3. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 322
  4. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  5. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  6. 2024LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contextscited by 240
  7. 2024CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMscited by 229
  8. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 218
  9. 2023Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?cited by 203
  10. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 193
  11. 2024MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGIcited by 192
  12. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 180
  13. 2025OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learningcited by 163
  14. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 129
  15. 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QAcited by 121
  16. 2024M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thoughtcited by 120
  17. 2025MMSearch-R1: Incentivizing LMMs to Searchcited by 120
  18. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 118
  19. 2024Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Modelscited by 112
  20. 2023Encyclopedic VQA: Visual questions about detailed properties of fine-grained categoriescited by 105
  21. 2024MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Enginescited by 98
  22. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  23. 2023Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillingscited by 68
  24. 2025SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Modelscited by 61
  25. 2024FullStack Bench: Evaluating LLMs as Full Stack Coderscited by 56
  26. 2023Calibrating LLM-Based Evaluatorcited by 53
  27. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agentscited by 49
  28. 2025A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applicationscited by 48
  29. 2025Open3D-VQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Spacecited by 37
  30. 2024MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Modelscited by 32
  31. 2023mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Modelcited by 31
  32. 2025MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Researchcited by 30
  33. 2025OAgents: An Empirical Study of Building Effective Agentscited by 28
  34. 2025OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoningcited by 25
  35. 2025Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)cited by 23
  36. 2024Assessing "Implicit" Retrieval Robustness of Large Language Modelscited by 9
  37. 2025Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experiencecited by 7
  38. 2025Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inferencecited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 31; 2026: 83.

114 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  2. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  3. 2025DeepEyesV2: Toward Agentic Multimodal Modelcited by 119
  4. 2025Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Searchcited by 116
  5. 2025Latent Visual Reasoningcited by 99
  6. 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agentscited by 71
  7. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 68
  8. 2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learningcited by 59
  9. 2025Towards General Agentic Intelligence via Environment Scalingcited by 51
  10. 2026REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agentscited by 43
  11. 2025Scaling Agents via Continual Pre-trainingcited by 39
  12. 2026Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agentscited by 37
38 more
  1. 2025MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agentscited by 35
  2. 2026Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Modelscited by 33
  3. 2025CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agentscited by 32
  4. 2025SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learningcited by 31
  5. 2026Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Modelscited by 30
  6. 2025Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoningcited by 28
  7. 2025Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearchcited by 25
  8. 2026Gen-Searcher: Reinforcing Agentic Search for Image Generationcited by 25
  9. 2026Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddingscited by 22
  10. 2026AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarioscited by 22
  11. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  12. 2026OmniGAIA: Towards Native Omni-Modal AI Agentscited by 21
  13. 2025A Survey on Agentic Multimodal Large Language Modelscited by 19
  14. 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baselinecited by 18
  15. 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agentscited by 18
  16. 2025ParallelMuse: Agentic Parallel Thinking for Deep Information Seekingcited by 14
  17. 2026VideoSeek: Long-Horizon Video Agent with Tool-Guided Seekingcited by 14
  18. 2025Reinforcement Learning Foundations for Deep Research Systems: A Surveycited by 13
  19. 2025ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoningcited by 13
  20. 2025InteractComp: Evaluating Search Agents With Ambiguous Queriescited by 12
  21. 2026DynaWeb: Model-Based Reinforcement Learning of Web Agentscited by 12
  22. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physicscited by 11
  23. 2026Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?cited by 11
  24. 2026Imagination Helps Visual Reasoning, But Not Yet in Latent Spacecited by 10
  25. 2025From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoningcited by 9
  26. 2025Video-Browser: Towards Agentic Open-web Video Browsingcited by 9
  27. 2026Towards Long-horizon Agentic Multimodal Searchcited by 9
  28. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  29. 2026TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agentscited by 8
  30. 2026VisBrowse-Bench: Benchmarking Visual-Native Search for Multimodal Browsing Agentscited by 8
  31. 2026HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agentscited by 8
  32. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  33. 2025MR2-Bench: Going Beyond Matching to Reasoning in Multimodal Retrievalcited by 7
  34. 2025Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworkscited by 7
  35. 2026WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoningcited by 7
  36. 2026MTA-Agent: An Open Recipe for Multimodal Deep Search Agentscited by 7
  37. 2025MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoningcited by 6
  38. 2026Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoningcited by 6

50 most cited of 114 All 114 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents
  2. 2026Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents
  3. 2025Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
  4. 2026Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
  5. 2026VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research
  6. 2025Rethinking the Design of Reinforcement Learning-Based Deep Research Agents
  7. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
  8. 2023Multimodal Web Navigation with Instruction-Finetuned Foundation Models