Metraipolis › archive › dc_a0f4a058a031

STEER: Route-Aware Adaptive Reasoning for Autonomous Driving — arXiv:2611.00718

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00718
License (as archived)
CC0-1.0
Archived
2026-11-03T18:57:01.376Z
SHA-256 of the archived text
e4eccd84d64ba44a8d83f121b30305fc7632f4aec30f918632171a6451713259
Stable URL of this page
https://metraipolis.com/documento/dc_a0f4a058a031

How to cite

STEER: Route-Aware Adaptive Reasoning for Autonomous Driving — arXiv:2611.00718 — arXiv (en), https://arxiv.org/abs/2611.00718 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0f4a058a031 (Metraipolis archive dc_a0f4a058a031, sha256 e4eccd84d64ba44a8d83f121b30305fc7632f4aec30f918632171a6451713259)
BibTeX
@misc{dca0f4a058a031,
  title = {STEER: Route-Aware Adaptive Reasoning for Autonomous Driving — arXiv:2611.00718},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00718},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0f4a058a031; sha256 e4eccd84d64ba44a8d83f121b30305fc7632f4aec30f918632171a6451713259},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00718. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language action (VLA) models excel for end-to-end autonomous driving, yet their tendency to over-invoke chain-of-thought (CoT) reasoning mirrors a human cognitive pitfall: overthinking. Just as deliberate reasoning can slow or mislead human judgment in routine tasks, excessive CoT in VLA incurs unnecessary compute overhead and can paradoxically degrade planning performance. Recent research tackles this via adaptive reasoning, which dynamically modulates inference complexity by selectively triggering CoT for complex scenes while responding directly to routine ones. While prior adaptive methods rely on implicit adaptation, recent work shows that explicitly optimizing the route between CoT and direct responses yields superior performance, assuming scene-difficulty annotations which are labor-intensive, poorly scalable, and prone to error due to the subjectivity of judging driving complexity. We explore, for the first time, whether adaptive reasoning with explicit route optimization can be achieved without any scene-difficulty labeling. We introduce STEER, a generic over-reasoning mitigation strategy featuring two key components: (i) routing uncertainty-aware rollout, which calibrates sampling to align routing diversity with model uncertainty; and (ii) cross-route advantage credit assignment, which introduces a differential metric to reinforce optimal routing decisions based on environmental rewards rather than subjective labels. Extensive experiments on NAVSIM v1/v2 demonstrate that STEER is competitive with state-of-the-art methods in both planning quality and the Pareto front of inference efficiency.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.00718 — 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 2026-11-03T18:17:07.710Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).