# Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning

arXiv: https://arxiv.org/abs/2510.23473 · HTML: https://mlsanity.com/paper/2510.23473/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 45)

- [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)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [STAR: A Benchmark for Situated Reasoning in Real-World Videos](https://mlsanity.com/paper/2405.09711/) (2024)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents](https://mlsanity.com/paper/2311.05437/) (2023)
- [Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition](https://mlsanity.com/paper/2501.03230/) (2024)
- [Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding](https://mlsanity.com/paper/2503.13377/) (2025)
- [Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?](https://mlsanity.com/paper/2505.21374/) (2025)
- [ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration](https://mlsanity.com/paper/2411.16044/) (2024)
- [CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding](https://mlsanity.com/paper/2412.12075/) (2024)
- [UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens](https://mlsanity.com/paper/2505.14671/) (2025)
- [Visual Agentic Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.14246/) (2025)
- [MC-LLaVA: Multi-Concept Personalized Vision-Language Model](https://mlsanity.com/paper/2411.11706/) (2024)
- [Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos](https://mlsanity.com/paper/2506.05302/) (2025)
- [MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning](https://mlsanity.com/paper/2506.05331/) (2025)

## Built on by (most cited first, 30 of 34)

- [LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling](https://mlsanity.com/paper/2511.20785/) (2025)
- [Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding](https://mlsanity.com/paper/2512.05774/) (2025)
- [Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning](https://mlsanity.com/paper/2601.23224/) (2026)
- [AdaTooler-V: Adaptive Tool-Use for Images and Videos](https://mlsanity.com/paper/2512.16918/) (2025)
- [Thinking in Streaming Video](https://mlsanity.com/paper/2603.12938/) (2026)
- [The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents](https://mlsanity.com/paper/2604.10577/) (2026)
- [OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention](https://mlsanity.com/paper/2602.05847/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding](https://mlsanity.com/paper/2602.04094/) (2026)
- [VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos](https://mlsanity.com/paper/2602.07801/) (2026)
- [VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification](https://mlsanity.com/paper/2604.01569/) (2026)
- [SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2512.13874/) (2025)
- [EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models](https://mlsanity.com/paper/2603.12252/) (2026)
- [EVA: Efficient Reinforcement Learning for End-to-End Video Agent](https://mlsanity.com/paper/2603.22918/) (2026)
- [ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning](https://mlsanity.com/paper/2605.20342/) (2026)
- [Boosting Reasoning in Large Multimodal Models via Activation Replay](https://mlsanity.com/paper/2511.19972/) (2025)
- [Watch, Remember, Reason: Human-View Video Understanding with MLLMs](https://mlsanity.com/paper/2606.07433/) (2026)
- [Video-Based Reward Modeling for Computer-Use Agents](https://mlsanity.com/paper/2603.10178/) (2026)
- [Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding](https://mlsanity.com/paper/2604.01002/) (2026)
- [Find, Fix, Reason: Context Repair for Video Reasoning](https://mlsanity.com/paper/2604.16243/) (2026)
- [VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation](https://mlsanity.com/paper/2605.16079/) (2026)
- [OmniReasoner: Thinking with Long Audio-Video via Native Tool Use](https://mlsanity.com/paper/2607.19339/) (2026)
- [VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding](https://mlsanity.com/paper/2606.05259/) (2026)
- [See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding](https://mlsanity.com/paper/2606.09064/) (2026)
- [Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence](https://mlsanity.com/paper/2607.15092/) (2026)
- [Online Video Agent Harness for Long Video Understanding](https://mlsanity.com/paper/2609.12818/) (2026)
- [STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models](https://mlsanity.com/paper/2605.26014/) (2026)
- [SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence](https://mlsanity.com/paper/2605.31529/) (2026)
- [Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering](https://mlsanity.com/paper/2608.04124/) (2026)
- [Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning](https://mlsanity.com/paper/2608.11260/) (2026)

## Abstract (arXiv)

Recent advances in image reasoning methods, particularly "Thinking with Images", have demonstrated remarkable success in Multimodal Large Language Models (MLLMs); however, this dynamic reasoning paradigm has not yet been extended to video reasoning tasks. In this paper, we propose Video-Thinker, which empowers MLLMs to think with videos by autonomously leveraging their intrinsic "grounding" and "captioning" capabilities to generate reasoning clues throughout the inference process. To spark this capability, we construct Video-Thinker-10K, a curated dataset featuring autonomous tool usage within chain-of-thought reasoning sequences. Our training strategy begins with Supervised Fine-Tuning (SFT) to learn the reasoning format, followed by Group Relative Policy Optimization (GRPO) to strengthen this reasoning capability. Through this approach, Video-Thinker enables MLLMs to autonomously navigate grounding and captioning tasks for video reasoning, eliminating the need for constructing and calling external tools. Extensive experiments demonstrate that Video-Thinker achieves significant performance gains on both in-domain tasks and challenging out-of-domain video reasoning benchmarks, including Video-Holmes, CG-Bench-Reasoning, and VRBench. Our Video-Thinker-7B substantially outperforms existing baselines such as Video-R1 and establishes state-of-the-art performance among 7B-sized MLLMs.