# DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking

arXiv: https://arxiv.org/abs/2507.20879 · HTML: https://mlsanity.com/paper/2507.20879/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning.
- Builds on 17 of its 54 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)
- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)
- End-to-end autonomous driving / [Reasoning VLA and VLM driving policies](https://mlsanity.com/driving/reasoning-vla-and-vlm-driving-policies/)

## Builds on (most cited first, 17 of 17)

- [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)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [GPT-Driver: Learning to Drive with GPT](https://mlsanity.com/paper/2310.01415/) (2023)
- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [Imagine while Reasoning in Space: Multimodal Visualization-of-Thought](https://mlsanity.com/paper/2501.07542/) (2025)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning](https://mlsanity.com/paper/2503.07608/) (2025)
- [Think Only When You Need with Large Hybrid-Reasoning Models](https://mlsanity.com/paper/2505.14631/) (2025)
- [AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving](https://mlsanity.com/paper/2505.15298/) (2025)
- [Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought](https://mlsanity.com/paper/2505.15510/) (2025)
- [Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization](https://mlsanity.com/paper/2504.18397/) (2025)
- [Transferable and Adaptable Driving Behavior Prediction](https://mlsanity.com/paper/2202.05140/) (2022)
- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://mlsanity.com/paper/2505.08854/) (2025)
- [LightEMMA: A Longitudinal Evaluation of Vision-Language Models for Autonomous Driving](https://mlsanity.com/paper/2505.00284/) (2025)

## Built on by (most cited first, 12 of 12)

- [Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future](https://mlsanity.com/paper/2512.16760/) (2025)
- [Think3D: Thinking with Space for Spatial Reasoning](https://mlsanity.com/paper/2601.13029/) (2026)
- [OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision](https://mlsanity.com/paper/2509.05578/) (2025)
- [NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning](https://mlsanity.com/paper/2602.21172/) (2026)
- [Learning Vision-Language-Action World Models for Autonomous Driving](https://mlsanity.com/paper/2604.09059/) (2026)
- [ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior](https://mlsanity.com/paper/2512.05745/) (2025)
- [See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection](https://mlsanity.com/paper/2604.24339/) (2026)
- [IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Driving](https://mlsanity.com/paper/2605.31476/) (2026)
- [PixelPilot: Scalable Vision-Language-Action Models for End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.04637/) (2026)
- [WorkDrive: Roadwork Chain of Causation for Autonomous Driving](https://mlsanity.com/paper/2607.14727/) (2026)
- [Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving](https://mlsanity.com/paper/2609.01659/) (2026)
- [Towards Active Cross-View Object Geo-Localization](https://mlsanity.com/paper/2609.19662/) (2026)

## Abstract (arXiv)

The advent of Vision-Language Models (VLMs) has significantly advanced end-to-end autonomous driving, demonstrating powerful reasoning abilities for high-level behavior planning tasks. However, existing methods are often constrained by a passive perception paradigm, relying solely on text-based reasoning. This passivity restricts the model's capacity to actively seek crucial visual evidence when faced with uncertainty. To address this, we introduce DriveAgent-R1, the first autonomous driving agent capable of active perception for planning. In complex scenarios, DriveAgent-R1 proactively invokes tools to perform visual reasoning, firmly grounding its decisions in visual evidence, thereby enhancing both interpretability and reliability. Furthermore, we propose a hybrid thinking framework, inspired by human driver cognitive patterns, allowing the agent to adaptively switch between efficient text-only reasoning and robust tool-augmented visual reasoning based on scene complexity. This capability is cultivated through a three-stage progressive training strategy, featuring a core Cascaded Reinforcement Learning (Cascaded RL) phase. Extensive experiments on the Drive-Internal dataset, which is rich in long-tail scenarios, and the public nuScenes dataset show that, with only 3B parameters, DriveAgent-R1 achieves competitive performance comparable to top closed model systems such as GPT-5 and to human driving proficiency while remaining deployment-friendly, offering a proven path toward building more intelligent autonomous driving systems.