# ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.21457 · HTML: https://mlsanity.com/paper/2505.21457/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 47 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [Magma: A Foundation Model for Multimodal AI Agents](https://mlsanity.com/paper/2502.13130/) (2025)
- [GRIT: Teaching MLLMs to Think with Images](https://mlsanity.com/paper/2505.15879/) (2025)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration](https://mlsanity.com/paper/2411.16044/) (2024)
- [R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning](https://mlsanity.com/paper/2503.05379/) (2025)
- [ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding](https://mlsanity.com/paper/2501.05452/) (2025)
- [Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models](https://mlsanity.com/paper/2403.12966/) (2024)
- [Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training](https://mlsanity.com/paper/2403.02325/) (2024)
- [Neural Modular Control for Embodied Question Answering](https://mlsanity.com/paper/1810.11181/) (2018)
- [SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation](https://mlsanity.com/paper/2502.13143/) (2025)
- [Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration](https://mlsanity.com/paper/2505.20256/) (2025)
- [Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks](https://mlsanity.com/paper/1709.00507/) (2017)

## Built on by (most cited first, 30 of 43)

- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search](https://mlsanity.com/paper/2509.07969/) (2025)
- [Perception-Aware Policy Optimization for Multimodal Reasoning](https://mlsanity.com/paper/2507.06448/) (2025)
- [Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning](https://mlsanity.com/paper/2510.12712/) (2025)
- [Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding](https://mlsanity.com/paper/2512.05774/) (2025)
- [LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning](https://mlsanity.com/paper/2509.24786/) (2025)
- [From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2509.25373/) (2025)
- [Simple o3: Towards Interleaved Vision-Language Reasoning](https://mlsanity.com/paper/2508.12109/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks](https://mlsanity.com/paper/2511.15065/) (2025)
- [Active Perception Agent for Omnimodal Audio-Video Understanding](https://mlsanity.com/paper/2512.23646/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom](https://mlsanity.com/paper/2602.01334/) (2026)
- [Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought](https://mlsanity.com/paper/2603.22847/) (2026)
- [Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning](https://mlsanity.com/paper/2603.28618/) (2026)
- [VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning](https://mlsanity.com/paper/2512.06373/) (2025)
- [Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images](https://mlsanity.com/paper/2512.17306/) (2025)
- [AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning](https://mlsanity.com/paper/2601.18631/) (2026)
- [Boosting Reasoning in Large Multimodal Models via Activation Replay](https://mlsanity.com/paper/2511.19972/) (2025)
- [Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization](https://mlsanity.com/paper/2604.06777/) (2026)
- [DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding](https://mlsanity.com/paper/2605.15542/) (2026)
- [VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual Grounding](https://mlsanity.com/paper/2509.24776/) (2025)
- [Thinking with Images via Self-Calling Agent](https://mlsanity.com/paper/2512.08511/) (2025)
- [MARBLE: Multi-Aspect Reward Balance for Diffusion RL](https://mlsanity.com/paper/2605.06507/) (2026)
- [Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding](https://mlsanity.com/paper/2509.04243/) (2025)
- [Beyond Accuracy: Evaluating Grounded Visual Evidence in Thinking with Images](https://mlsanity.com/paper/2601.11633/) (2026)
- [StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision](https://mlsanity.com/paper/2603.06032/) (2026)
- [Latent Visual States for Efficient Multimodal Reasoning](https://mlsanity.com/paper/2606.24233/) (2026)
- [CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision](https://mlsanity.com/paper/2605.19538/) (2026)
- [Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?](https://mlsanity.com/paper/2606.01247/) (2026)

## Abstract (arXiv)

Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant information. It is a critical component of efficient perception and decision-making in humans and advanced embodied agents. With the rise of Multimodal Large Language Models (MLLMs) as central planners in robotic systems, the lack of methods for equipping MLLMs with active perception has become a key gap. We first provide a systematic definition of MLLM-based active perception tasks and show that GPT-o3's zoom-in strategy can be viewed as a special case, though it suffers from low efficiency and inaccurate region selection. To address these issues, we propose ACTIVE-o3, a reinforcement learning framework built on GRPO that equips MLLMs with active perception capabilities. Leveraging a modular sensing-action design and a dual-form reward, ACTIVE-o3 autonomously learns efficient and stable region selection strategies without explicit region-selection supervision. We further establish a comprehensive benchmark covering both open-world tasks, including small- and dense-object grounding, and domain-specific scenarios, including remote sensing, autonomous driving, and interactive segmentation. Experimental results demonstrate that ACTIVE-o3 significantly enhances active perception capabilities compared to baselines. Moreover, we show that our framework not only preserves the model's general understanding ability but can also serve as a proxy task for leveraging perception data, further improving performance on benchmarks such as RealWorldQA and MME.