mlsanityData to 7 Oct 2026

SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search

arXiv 2606.31504 ↗First posted 30 Jun 2026cs.CVcited by 1

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

Abstract (arXiv)

We present SimpleSearch-VL, an efficient, reliable, and practical framework for multimodal agentic search. Its core idea is to improve the agent's own search-and-verification process rather than scaling data, tools, or auxiliary model components. For efficiency, Factorized Adaptive Rollout (FAR) improves sampling efficiency by forming more informative training groups while using redundant samples to mitigate long-tail latency and expose hard samples. For reliability, SimpleSearch-VL performs evidence-verified reasoning, explicitly using chain-of-thought verification to assess the relevance of retrieved visual and textual cues to the original context. For practicality, SimpleSearch-VL keeps a lightweight tool interface and performs webpage self-summary within the agent, requiring no additional external dependencies. With only 5K supervised tool-interleaved trajectories and 2K RL data, SimpleSearch-VL improves Qwen3-VL agentic baselines by 15.8 and 16.0 average points for the 8B and 30B-A3B variants, respectively. The SimpleSearch-VL-30B-A3B model further achieves performance competitive with agentic Gemini-3-Pro.

Key facts. Cited by 1 paper 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 43 of its 51 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

43 of 51 references.

Closest ancestors · 7

Same direction, newest first

  1. 2026Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning13 Jun
  2. 2026From Web to Pixels: Bringing Agentic Search into Visual Perception12 May
  3. 2026Towards Long-horizon Agentic Multimodal Search14 Apr
  4. 2026MTA-Agent: An Open Recipe for Multimodal Deep Search Agents7 Apr
  5. 2025SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning30 Dec
  6. 2025DeepEyesV2: Toward Agentic Multimodal Model7 Nov
  7. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent7 Aug

Other references · 36

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  7. 2025Qwen3-VL Technical Reportcited by 2,534
  8. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  9. 2024SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuningcited by 345
  10. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documentscited by 237
  11. 2023Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?cited by 203
  12. 2016FVQA: Fact-based Visual Question Answeringcited by 181
24 more
  1. 2025Agentic Reinforced Policy Optimizationcited by 166
  2. 2025MMSearch-R1: Incentivizing LMMs to Searchcited by 120
  3. 2025Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rolloutscited by 108
  4. 2025MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scalingcited by 72
  5. 2025SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Modelscited by 61
  6. 2025No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shapingcited by 48
  7. 2026REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agentscited by 43
  8. 2025DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Searchcited by 41
  9. 2025Laminar: A Scalable Asynchronous RL Post-Training Frameworkcited by 35
  10. 2026Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Modelscited by 33
  11. 2026OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Datacited by 32
  12. 2026OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesiscited by 32
  13. 2026Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Modelscited by 30
  14. 2025Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reusecited by 28
  15. 2025APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generationcited by 27
  16. 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baselinecited by 18
  17. 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agentscited by 18
  18. 2026Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewardscited by 15
  19. 2026Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learningcited by 13
  20. 2025VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RLcited by 9
  21. 2026Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learningcited by 8
  22. 2026HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agentscited by 8
  23. 2026Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generationcited by 4
  24. 2025CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Samplingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LiteSearch-VL: Small Multimodal Search Agents via Trajectory Distillation and Synthetic Step-DPO
  2. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
  3. 2026ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
  4. 2026WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents
  5. 2026InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
  6. 2025RAVine: Reality-Aligned Evaluation for Agentic Search
  7. 2025Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
  8. 2026BrowseComp-V3: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents