# AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving

arXiv: https://arxiv.org/abs/2505.15298 · HTML: https://mlsanity.com/paper/2505.15298/

## Key facts

- Cited by 35 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 29 of its 49 references that are in the map.
- First posted on arXiv 21 May 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, 29 of 29)

- [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)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [GPT-Driver: Learning to Drive with GPT](https://mlsanity.com/paper/2310.01415/) (2023)
- [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2503.12937/) (2025)
- [DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving](https://mlsanity.com/paper/2312.09245/) (2023)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2309.16292/) (2023)
- [Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search](https://mlsanity.com/paper/2412.18319/) (2024)
- [Ovis: Structural Embedding Alignment for Multimodal Large Language Model](https://mlsanity.com/paper/2405.20797/) (2024)
- [A Language Agent for Autonomous Driving](https://mlsanity.com/paper/2311.10813/) (2023)
- [LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs](https://mlsanity.com/paper/2501.06186/) (2025)
- [OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning](https://mlsanity.com/paper/2504.04348/) (2025)
- [Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives](https://mlsanity.com/paper/2501.04003/) (2025)
- [Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1907.05774/) (2019)
- [AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning](https://mlsanity.com/paper/2503.07608/) (2025)
- [PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving](https://mlsanity.com/paper/2404.14327/) (2024)
- [DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving](https://mlsanity.com/paper/2403.16996/) (2024)
- [VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving](https://mlsanity.com/paper/2412.15544/) (2024)
- [DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding](https://mlsanity.com/paper/2503.10621/) (2025)
- [SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models](https://mlsanity.com/paper/2411.13112/) (2024)
- [OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning](https://mlsanity.com/paper/2405.01533/) (2024)
- [FASIONAD++ : Integrating High-Level Instruction and Information Bottleneck in FAt-Slow fusION Systems for Enhanced Safety in Autonomous Driving with Adaptive Feedback](https://mlsanity.com/paper/2503.08162/) (2025)
- [LEGO-Motion: Learning-Enhanced Grids with Occupancy Instance Modeling for Class-Agnostic Motion Prediction](https://mlsanity.com/paper/2503.07367/) (2025)
- [How Cars Move: Analyzing Driving Dynamics for Safer Urban Traffic](https://mlsanity.com/paper/2412.04020/) (2024)

## Built on by (most cited first, 30 of 35)

- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [A Survey on Vision-Language-Action Models for Autonomous Driving](https://mlsanity.com/paper/2506.24044/) (2025)
- [TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics](https://mlsanity.com/paper/2510.07181/) (2025)
- [Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools](https://mlsanity.com/paper/2510.08480/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning](https://mlsanity.com/paper/2602.21172/) (2026)
- [Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2505.20223/) (2025)
- [DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking](https://mlsanity.com/paper/2507.20879/) (2025)
- [EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving](https://mlsanity.com/paper/2508.09158/) (2025)
- [MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2512.04441/) (2025)
- [SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios](https://mlsanity.com/paper/2602.08440/) (2026)
- [Learning Vision-Language-Action World Models for Autonomous Driving](https://mlsanity.com/paper/2604.09059/) (2026)
- [Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language Models](https://mlsanity.com/paper/2604.01259/) (2026)
- [MTRDrive: Memory-Tool Synergistic Reasoning for Robust Autonomous Driving in Corner Cases](https://mlsanity.com/paper/2509.20843/) (2025)
- [OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving](https://mlsanity.com/paper/2512.14044/) (2025)
- [On the Generalization Capacities of MLLMs for Spatial Intelligence](https://mlsanity.com/paper/2603.06704/) (2026)
- [LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving](https://mlsanity.com/paper/2508.12404/) (2025)
- [DriveVLM-RL: Neuroscience-Inspired Reinforcement Learning with Vision-Language Models for Safe and Deployable Autonomous Driving](https://mlsanity.com/paper/2603.18315/) (2026)
- [DriveCritic: Towards Context-Aware, Human-Aligned Evaluation for Autonomous Driving with Vision-Language Models](https://mlsanity.com/paper/2510.13108/) (2025)
- [Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challenges](https://mlsanity.com/paper/2512.00021/) (2025)
- [Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer](https://mlsanity.com/paper/2602.19058/) (2026)
- [See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection](https://mlsanity.com/paper/2604.24339/) (2026)
- [FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems](https://mlsanity.com/paper/2509.24408/) (2025)
- [SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving](https://mlsanity.com/paper/2510.18123/) (2025)
- [Smooth Operator: Smooth Verifiable Reward Activates Spatial Reasoning Ability of Vision-Language Model](https://mlsanity.com/paper/2601.07695/) (2026)
- [CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving](https://mlsanity.com/paper/2607.04179/) (2026)
- [Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving](https://mlsanity.com/paper/2604.03497/) (2026)
- [WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.08375/) (2026)
- [GPU Memory Prediction for Multimodal Model Training](https://mlsanity.com/paper/2512.07853/) (2025)

## Abstract (arXiv)

Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome this, we introduce AgentThink, a pioneering unified framework that integrates Chain-of-Thought (CoT) reasoning with dynamic, agent-style tool invocation for autonomous driving tasks. AgentThink's core innovations include: (i) Structured Data Generation, which establishes an autonomous driving tool library to automatically construct structured, self-verified reasoning data explicitly incorporating tool usage for diverse driving scenarios; (ii) A Two-stage Training Pipeline, employing Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO) to equip VLMs with the capability for autonomous tool invocation; and (iii) Agent-style Tool-Usage Evaluation, introducing a novel multi-tool assessment protocol to rigorously evaluate the model's tool invocation and utilization. Experiments on the DriveLMM-o1 benchmark demonstrate that AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54%, while markedly improving reasoning quality and consistency. Furthermore, ablation studies and robust zero-shot/few-shot generalization experiments across various benchmarks underscore its powerful capabilities. These findings highlight a promising trajectory for developing trustworthy and tool-aware autonomous driving models. Code is available at https://github.com/curryqka/AgentThink.