# PKRD-CoT: A Unified Chain-of-thought Prompting for Multi-Modal Large Language Models in Autonomous Driving

arXiv: https://arxiv.org/abs/2412.02025 · HTML: https://mlsanity.com/paper/2412.02025/

## Key facts

- Cited by 17 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 26 of its 40 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## 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 / [Large language models for driving](https://mlsanity.com/driving/large-language-models-for-driving/)

## Builds on (most cited first, 26 of 26)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023)
- [MM-LLMs: Recent Advances in MultiModal Large Language Models](https://mlsanity.com/paper/2401.13601/) (2024)
- [DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving](https://mlsanity.com/paper/2312.09245/) (2023)
- [Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving](https://mlsanity.com/paper/2310.01957/) (2023)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2309.16292/) (2023)
- [Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages](https://mlsanity.com/paper/2310.14799/) (2023)
- [Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models](https://mlsanity.com/paper/2310.17642/) (2023)
- [Towards Knowledge-driven Autonomous Driving](https://mlsanity.com/paper/2312.04316/) (2023)
- [BEVGPT: Generative Pre-trained Large Model for Autonomous Driving Prediction, Decision-Making, and Planning](https://mlsanity.com/paper/2310.10357/) (2023)
- [Parameterized Decision-making with Multi-modal Perception for Autonomous Driving](https://mlsanity.com/paper/2312.11935/) (2023)
- [Real-Time Capable Decision Making for Autonomous Driving Using Reachable Sets](https://mlsanity.com/paper/2309.12289/) (2023)
- [Leveraging Zero-Shot Prompting for Efficient Language Model Distillation](https://mlsanity.com/paper/2403.15886/) (2024)

## Built on by (most cited first, 17 of 17)

- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models](https://mlsanity.com/paper/2504.08813/) (2025)
- [V2X-UniPool: Unifying Multimodal Perception and Knowledge Reasoning for Autonomous Driving](https://mlsanity.com/paper/2506.02580/) (2025)
- [Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2505.20223/) (2025)
- [SenseRAG: Constructing Environmental Knowledge Bases with Proactive Querying for LLM-Based Autonomous Driving](https://mlsanity.com/paper/2501.03535/) (2025)
- [X-Driver: Explainable Autonomous Driving with Vision-Language Models](https://mlsanity.com/paper/2505.05098/) (2025)
- [SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs](https://mlsanity.com/paper/2503.08884/) (2025)
- [Evaluation of LLMs for mathematical problem solving](https://mlsanity.com/paper/2506.00309/) (2025)
- [WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification](https://mlsanity.com/paper/2509.17740/) (2025)
- [PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenario](https://mlsanity.com/paper/2504.05908/) (2025)
- [From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models](https://mlsanity.com/paper/2511.12861/) (2025)
- [MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models](https://mlsanity.com/paper/2512.05530/) (2025)
- [X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles](https://mlsanity.com/paper/2602.13248/) (2026)
- [KnowDiffuser: A Knowledge-Guided Diffusion Planner with LLM Reasoning](https://mlsanity.com/paper/2603.10441/) (2026)
- [Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding](https://mlsanity.com/paper/2607.24199/) (2026)

## Abstract (arXiv)

There is growing interest in leveraging the capabilities of robust Multi-Modal Large Language Models (MLLMs) directly within autonomous driving contexts. However, the high costs and complexity of designing and training end-to-end autonomous driving models make them challenging for many enterprises and research entities. To address this, our study explores a seamless integration of MLLMs into autonomous driving systems by proposing a Zero-Shot Chain-of-Thought (Zero-Shot-CoT) prompt design named PKRD-CoT. PKRD-CoT is based on the four fundamental capabilities of autonomous driving: perception, knowledge, reasoning, and decision-making. This makes it particularly suitable for understanding and responding to dynamic driving environments by mimicking human thought processes step by step, thus enhancing decision-making in real-time scenarios. Our design enables MLLMs to tackle problems without prior experience, thereby increasing their utility within unstructured autonomous driving environments. In experiments, we demonstrate the exceptional performance of GPT-4.0 with PKRD-CoT across autonomous driving tasks, highlighting its effectiveness in autonomous driving scenarios. Additionally, our benchmark analysis reveals the promising viability of PKRD-CoT for other MLLMs, such as Claude, LLava1.6, and Qwen-VL-Plus. Overall, this study contributes a novel and unified prompt-design framework for GPT-4.0 and other MLLMs in autonomous driving, while also rigorously evaluating the efficacy of these widely recognized MLLMs in the autonomous driving domain through comprehensive comparisons.