Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

Accepted at EMNLP 2026, this survey reviews 171 papers and proposes a representation-centered taxonomy that sorts autonomous-driving reasoning methods into language-based, visual-spatial, latent-dynamic, and externalized categories, arguing that the field's open frontier is intermediate representations that are grounded in the real world, coupled to real-time action, and verifiable in safety-critical systems.

SourcearXiv Computer VisionAuthor: Zhengxu Tang, Xiaozhou Zhang, Guofeng Cui, Ziyu Gong, Zi Wang, Yunfei Shi, Ruifeng Deng, Chengzhi Qi, Ke Chen, Sachin Patil, Tianjun Xiao, Langechuan Liu, Pichao Wang
Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 31 Aug 2026]

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

View a PDF of the paper titled Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving, by Zhengxu Tang and 12 other authors

View PDF HTML (experimental)

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: this https URL.

Comments: Accepted by EMNLP 2026

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL); Robotics (cs.RO)

Cite as: arXiv:2609.01659 [cs.CV]

(or arXiv:2609.01659v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.01659

arXiv-issued DOI via DataCite

Submission history

From: Pichao Wang [view email] [v1] Mon, 31 Aug 2026 18:16:11 UTC (17,445 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving, by Zhengxu Tang and 12 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-09

Change to browse by:

cs cs.CL cs.RO

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersIntermediate

Key points

  • The survey covers 171 papers, including 130 method papers and 41 benchmarks, datasets, surveys, and analysis papers.
  • It introduces a representation-centered taxonomy organized by the form of the intermediate state, dividing 130 methods into four categories and 13 subtypes.
  • Core claim: because the output of driving is a continuous action, its reasoning must share the same spatiotemporal structure as the physical world.
  • The open frontier is intermediate representations that can be grounded in reality, coupled to real-time action, and verified under safety-critical constraints.

Highlights and analysis are generated automatically and may contain errors. Check the original source.