# OneThinker: All-in-one Reasoning Model for Image and Video

arXiv: https://arxiv.org/abs/2512.03043 · HTML: https://mlsanity.com/paper/2512.03043/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 82 of its 86 references that are in the map.
- First posted on arXiv 2 Dec 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 82)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?](https://mlsanity.com/paper/2403.14624/) (2024)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)

## Built on by (most cited first, 30 of 56)

- [Gen-Searcher: Reinforcing Agentic Search for Image Generation](https://mlsanity.com/paper/2603.28767/) (2026)
- [EditThinker: Unlocking Iterative Reasoning for Any Image Editor](https://mlsanity.com/paper/2512.05965/) (2025)
- [Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification](https://mlsanity.com/paper/2601.15808/) (2026)
- [Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously](https://mlsanity.com/paper/2603.12262/) (2026)
- [AdaTooler-V: Adaptive Tool-Use for Images and Videos](https://mlsanity.com/paper/2512.16918/) (2025)
- [OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents](https://mlsanity.com/paper/2605.05185/) (2026)
- [Vision-aligned Latent Reasoning for Multi-modal Large Language Model](https://mlsanity.com/paper/2602.04476/) (2026)
- [Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis](https://mlsanity.com/paper/2603.29620/) (2026)
- [Wall-OSS-0.5 Technical Report](https://mlsanity.com/paper/2605.30877/) (2026)
- [VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning](https://mlsanity.com/paper/2602.08828/) (2026)
- [Vero: An Open RL Recipe for General Visual Reasoning](https://mlsanity.com/paper/2604.04917/) (2026)
- [Dual Latent Memory for Visual Multi-agent System](https://mlsanity.com/paper/2602.00471/) (2026)
- [CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning](https://mlsanity.com/paper/2602.00181/) (2026)
- [AdaCodec: A Predictive Visual Code for Video MLLMs](https://mlsanity.com/paper/2606.02569/) (2026)
- [Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search](https://mlsanity.com/paper/2602.04454/) (2026)
- [From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models](https://mlsanity.com/paper/2605.20177/) (2026)
- [Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models](https://mlsanity.com/paper/2606.11324/) (2026)
- [A Benchmark for Omni-Modal Reasoning in Long Videos](https://mlsanity.com/paper/2512.16978/) (2025)
- [Co-Evolving Policy Distillation](https://mlsanity.com/paper/2604.27083/) (2026)
- [Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs](https://mlsanity.com/paper/2605.00814/) (2026)
- [Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs](https://mlsanity.com/paper/2608.20492/) (2026)
- [Visual Enhanced Depth Scaling for Multimodal Latent Reasoning](https://mlsanity.com/paper/2604.10500/) (2026)
- [From Web to Pixels: Bringing Agentic Search into Visual Perception](https://mlsanity.com/paper/2605.12497/) (2026)
- [Temporal-Aware Reasoning Optimization for Video Temporal Grounding](https://mlsanity.com/paper/2606.09248/) (2026)
- [CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts](https://mlsanity.com/paper/2606.31986/) (2026)
- [OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks](https://mlsanity.com/paper/2604.08539/) (2026)
- [Agentic AI for Remote Sensing: Technical Challenges and Research Directions](https://mlsanity.com/paper/2604.24919/) (2026)
- [Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning](https://mlsanity.com/paper/2605.09640/) (2026)
- [VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding](https://mlsanity.com/paper/2606.05259/) (2026)
- [From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models](https://mlsanity.com/paper/2512.10867/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typically train separate models for different tasks and treat image and video reasoning as disjoint domains. This results in limited scalability toward a multimodal reasoning generalist, which restricts practical versatility and hinders potential knowledge sharing across tasks and modalities. To this end, we propose OneThinker, an all-in-one reasoning model that unifies image and video understanding across diverse fundamental visual tasks, including question answering, captioning, spatial and temporal grounding, tracking, and segmentation. To achieve this, we construct the OneThinker-600k training corpus covering all these tasks and employ commercial models for CoT annotation, resulting in OneThinker-SFT-340k for SFT cold start. Furthermore, we propose EMA-GRPO to handle reward heterogeneity in multi-task RL by tracking task-wise moving averages of reward standard deviations for balanced optimization. Extensive experiments on diverse visual benchmarks show that OneThinker delivers strong performance on 31 benchmarks, across 10 fundamental visual understanding tasks. Moreover, it exhibits effective knowledge transfer between certain tasks and preliminary zero-shot generalization ability, marking a step toward a unified multimodal reasoning generalist. All code, model, and data are released.