# CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting

arXiv: https://arxiv.org/abs/2503.07234 · HTML: https://mlsanity.com/paper/2503.07234/

## Key facts

- Cited by 26 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 4 of its 66 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)
- End-to-end autonomous driving / [Large language models for driving](https://mlsanity.com/driving/large-language-models-for-driving/)
- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 4 of 4)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [NEST: A Neuromodulated Small-world Hypergraph Trajectory Prediction Model for Autonomous Driving](https://mlsanity.com/paper/2412.11682/) (2024)

## Built on by (most cited first, 26 of 26)

- [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs](https://mlsanity.com/paper/2507.02076/) (2025)
- [DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale](https://mlsanity.com/paper/2604.00813/) (2026)
- [Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2505.20223/) (2025)
- [Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language Models](https://mlsanity.com/paper/2604.01259/) (2026)
- [X-Driver: Explainable Autonomous Driving with Vision-Language Models](https://mlsanity.com/paper/2505.05098/) (2025)
- [Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Prediction](https://mlsanity.com/paper/2505.06856/) (2025)
- [AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Prediction](https://mlsanity.com/paper/2507.01801/) (2025)
- [RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System](https://mlsanity.com/paper/2511.18286/) (2025)
- [Large Foundation Models for Trajectory Prediction in Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2509.10570/) (2025)
- [SafeCast: Risk-Responsive Motion Forecasting for Autonomous Vehicles](https://mlsanity.com/paper/2503.22541/) (2025)
- [Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles](https://mlsanity.com/paper/2512.03454/) (2025)
- [E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving](https://mlsanity.com/paper/2512.04733/) (2025)
- [Listen, Look, Drive: Coupling Audio Instructions for User-aware VLA-based Autonomous Driving](https://mlsanity.com/paper/2601.12142/) (2026)
- [Addressing Corner Cases in Autonomous Driving: A World Model-based Approach with Mixture of Experts and LLMs](https://mlsanity.com/paper/2510.21867/) (2025)
- [SVBRD-LLM: Self-Verifying Behavioral Rule Discovery for Autonomous Vehicle Identification](https://mlsanity.com/paper/2511.14977/) (2025)
- [COVLM-RL: Critical Object-Oriented Reasoning for Autonomous Driving Using VLM-Guided Reinforcement Learning](https://mlsanity.com/paper/2512.09349/) (2025)
- [Towards Human-Like Trajectory Prediction for Autonomous Driving: A Behavior-Centric Approach](https://mlsanity.com/paper/2505.21565/) (2025)
- [SAIL: Scene-aware Adaptive Iterative Learning for Long-Tail Trajectory Prediction in Autonomous Vehicles](https://mlsanity.com/paper/2604.04573/) (2026)
- [Steins;Gate Drive: Semantic Safety Arbitration over Structured Futures for Latency-Decoupled LLM Planning](https://mlsanity.com/paper/2605.22456/) (2026)
- [GraphBEV++: Multi-Modal Feature Alignment for Autonomous Driving](https://mlsanity.com/paper/2606.16354/) (2026)
- [SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving](https://mlsanity.com/paper/2607.09741/) (2026)
- [Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding](https://mlsanity.com/paper/2607.24199/) (2026)
- [A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform](https://mlsanity.com/paper/2610.00926/) (2026)

## Abstract (arXiv)

Accurate motion forecasting is crucial for safe autonomous driving (AD). This study proposes CoT-Drive, a novel approach that enhances motion forecasting by leveraging large language models (LLMs) and a chain-of-thought (CoT) prompting method. We introduce a teacher-student knowledge distillation strategy to effectively transfer LLMs' advanced scene understanding capabilities to lightweight language models (LMs), ensuring that CoT-Drive operates in real-time on edge devices while maintaining comprehensive scene understanding and generalization capabilities. By leveraging CoT prompting techniques for LLMs without additional training, CoT-Drive generates semantic annotations that significantly improve the understanding of complex traffic environments, thereby boosting the accuracy and robustness of predictions. Additionally, we present two new scene description datasets, Highway-Text and Urban-Text, designed for fine-tuning lightweight LMs to generate context-specific semantic annotations. Comprehensive evaluations of five real-world datasets demonstrate that CoT-Drive outperforms existing models, highlighting its effectiveness and efficiency in handling complex traffic scenarios. Overall, this study is the first to consider the practical application of LLMs in this field. It pioneers the training and use of a lightweight LLM surrogate for motion forecasting, setting a new benchmark and showcasing the potential of integrating LLMs into AD systems.