paper-with-me

홈 › Papers

Accelerating Structured Chain-of-Thought in Autonomous Vehicles

2026-02-02 · Yi Gu, Yan Wang, Yuxiao Chen, Yurong You, Wenjie Luo, Yue Wang, Wenhao Ding, Boyi Li, Heng Yang, Boris Ivanovic, Marco Pavone arxiv

Chain-of-Thought (CoT) reasoning enhances the decision-making capabilities of vision-language-action models in autonomous driving, but its autoregressive nature introduces significant inference latency, making it impractical for real-time applications. To address this, we introduce FastDriveCoT, a novel parallel decoding method that accelerates template-structured CoT. Our approach decomposes the reasoning process into a dependency graph of distinct sub-tasks, such as identifying critical objects and summarizing traffic rules, some of which can be generated in parallel. By generating multiple independent reasoning steps concurrently within a single forward pass, we significantly reduce the number of sequential computations. Experiments demonstrate a 3-4$\times$ speedup in CoT generation and a substantial reduction in end-to-end latency across various model architectures, all while preserving the original downstream task improvements brought by incorporating CoT reasoning.

📄 PDF Abstract BibTeX arXiv:2602.02864

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous VehiclesAutonomous Driving

Similar Papers 제목 키워드 기반

Receive, Reason, and React: Drive as You Say with Large Language Models in Autonomous Vehicles

2023-10-12 · Can Cui, Yunsheng Ma, Xu Cao, Wenqian Ye 외

The fusion of human-centric design and artificial intelligence (AI) capabilities has opened up new possibilities for next-generation autonomous vehicles that go beyond transportation. These vehicles can dynamically inter…

Autonomous DrivingAutonomous VehiclesDecision Making

TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning

2025-02-03 · Chengkai Xu, Jiaqi Liu, Shiyu Fang, Yiming Cui 외

Although Deep Reinforcement Learning (DRL) and Large Language Models (LLMs) each show promise in addressing decision-making challenges in autonomous driving, DRL often suffers from high sample complexity, while LLMs have…

Autonomous DrivingDecision MakingDeep Reinforcement Learning

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

2024-12-02 · Xuewen Luo, Fan Ding, Yinsheng Song, Xiaofeng Zhang 외

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 e…

Autonomous DrivingDecision Making

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

2025-05-21 · Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo 외

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 reas…

Autonomous Driving

Latent Chain-of-Thought Improves Structured-Data Transformers

2026-05-11 · Carson Dudley, Samet Oymak arxiv

Chain-of-thought and more broadly test-time compute are known to augment the expressive capabilities of language models and have led to major innovations in reasoning. Motivated by this success, this paper explores laten…