Metraipolis › archive › dc_7fbd40656ede

XCoT-VLA: Executable Chain-of-Thought for Vision-Language-Action Driving — arXiv:2608.10976

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.10976
License (as archived): CC0-1.0
Archived: 2026-10-19T06:08:40.628Z
SHA-256 of the archived text: 4af35fa8ae61de5eeb0f5efee2a6f2988604eeb30154875073f17ba998a97653
Stable URL of this page: https://metraipolis.com/documento/dc_7fbd40656ede

How to cite

XCoT-VLA: Executable Chain-of-Thought for Vision-Language-Action Driving — arXiv:2608.10976 — arXiv (en), https://arxiv.org/abs/2608.10976 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fbd40656ede (Metraipolis archive dc_7fbd40656ede, sha256 4af35fa8ae61de5eeb0f5efee2a6f2988604eeb30154875073f17ba998a97653)

BibTeX

@misc{dc7fbd40656ede,
  title = {XCoT-VLA: Executable Chain-of-Thought for Vision-Language-Action Driving — arXiv:2608.10976},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10976},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fbd40656ede; sha256 4af35fa8ae61de5eeb0f5efee2a6f2988604eeb30154875073f17ba998a97653},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10976. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models can connect scene understanding, semantic reasoning, and trajectory generation for autonomous driving. However, verbose natural-language Chain-of-Thought (CoT) is poorly suited to real-time control because it is open-ended, costly to decode, and difficult to optimize as an action-facing representation. We propose XCoT-VLA, which replaces descriptive rationales with compact executable CoT tokens learned from automatically constructed Reason-Action supervision. Logged trajectories provide action evidence, while scene context supplies causal semantics. The predicted XCoT sequence remains in context and conditions fixed trajectory queries through shared multimodal self-attention. Deterministic token-function routing applies the Reason FFN to XCoT tokens and the Control FFN to trajectory queries for flow-matching trajectory generation. We further introduce XCoT Policy Optimization (XCPO) as an optional refinement extension in the same executable token space. XCoT-VLA reduces longitudinal ADE from 1.645 to 1.323 on a general-distribution set and lateral FDE from 1.616 to 0.648 in lane-change scenarios. By representing driving-oriented reasoning with only 2-6 executable XCoT tokens, our method substantially reduces autoregressive reasoning overhead and remains within the real-time planning budget. These results demonstrate that driving-oriented reasoning can be compact, executable, and directly connected to trajectory generation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.10976 — 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 2026-10-19T05:57:28.307Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).