Metraipolis › archive › dc_7449680214fa

Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving — arXiv:2609.01659

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01659
License (as archived)
CC0-1.0
Archived
2026-10-17T04:17:00.044Z
SHA-256 of the archived text
0b26c4d272ea724d5344c507c709cd0b06c487c4eeaf3daae1cc40e289252a6a
Stable URL of this page
https://metraipolis.com/documento/dc_7449680214fa

How to cite

Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving — arXiv:2609.01659 — arXiv (en), https://arxiv.org/abs/2609.01659 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7449680214fa (Metraipolis archive dc_7449680214fa, sha256 0b26c4d272ea724d5344c507c709cd0b06c487c4eeaf3daae1cc40e289252a6a)
BibTeX
@misc{dc7449680214fa,
  title = {Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving — arXiv:2609.01659},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01659},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7449680214fa; sha256 0b26c4d272ea724d5344c507c709cd0b06c487c4eeaf3daae1cc40e289252a6a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01659. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CL).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.01659 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T03:26:49.821Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).