Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving

2026-08-31

AI Summary

该研究解决了自动驾驶中从文本链式思维到基于动作的推理转变问题，通过分析171篇论文，提出了一种以表示为中心的分类方法。

Abstract

Chain-of-thought (CoT) reasoning powers generative models by eliciting intermediate steps before producing an answer. In autonomous driving, the answer is a continuous action. Thus its reasoning must share the same spatiotemporal structure as the physical world. This survey studies the resulting shift from textual CoT to action-grounded reasoning. Surveying 171 papers, including 130 method papers and 41 benchmarks, datasets, surveys, and analysis papers, we propose a representation-centered taxonomy that treats the form of the intermediate state as the organizing axis. We systematize the 130 methods into four categories: language-based, visual-spatial, latent-dynamic, and externalized reasoning, further divided into 13 subtypes tied to distinct regions of interests. Our synthesis shows that the open frontier of reasoning in driving agents lies in intermediate representations that can be grounded in the real world, coupled to real-time action, and verified under safety-critical systems. Project page: https://github.com/tangzhengxu/awesome-av-cot.

Problem

• Action-Grounded Reasoning
• Autonomous Driving
• Chain-of-Thought

Innovation

• action-grounded reasoning
• representation-centered taxonomy
• spatiotemporal structure
• autonomous driving