arXiv:2609.15169v1 Announce Type: new Abstract: Driving vision-language-action (VLA) models increasingly reason before acting, but their intermediate reasoning is often weakly grounded in physical sc...
The paper surveys the transition from textual chain-of-thought reasoning to action-grounded reasoning in autonomous driving, highlighting that driving decisions require continuous actions that mirror the spatiotemporal structure of the physical world. It reviews 171 papers, categorizing 130 methods into four main types—language-based, visual-spatial, latent-dynamic, and externalized reasoning—along with 13 subtypes linked to specific regions of interest. The authors argue that the future of driving agent reasoning lies in intermediate representations that are grounded in reality, linked to real-time actions, and verifiable within safety-critical systems.
arXiv:2606. 23938v1 Announce Type: new Abstract: Driving VLA models incorporating Chain-of-Thought (CoT) reasoning are attractive because they leverage pretrained VLM representations and expose intermediate decisions in natural language, yet current rationales often lack the step-by-step decision semantics needed to keep the rationale causally connected to the planned motion.
arXiv:2609. 28366v1 Announce Type: cross Abstract: Vision-language models (VLMs) offer a promising approach to long-tail autonomous driving, but existing driving datasets provide limited supervision for connecting decision-critical visual evidence with reasoning and planning.
The paper introduces the KITScenes LongTail dataset, a curated collection of rare driving scenarios designed to evaluate how well reasoning models in autonomous driving follow their own reasoning. The authors find that many current models frequently diverge between the actions they state in their reasoning chains and the actions they actually execute, a phenomenon they term incoherence. They show that when the reasoning and execution disagree, the reasoning is often correct, and enforcing coherence via a kinematic model can improve motion planning, indicating that coherent action based on stated reasoning is essential for trustworthy autonomous driving.
arXiv:2610.10390v1 Announce Type: new Abstract: Vision-language-action~(VLA) models have emerged as a promising paradigm for autonomous driving. However, existing VLA models still suffer from a funda...
arXiv:2605.10426v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing reasoning mecha...
arXiv:2608. 01755v2 Announce Type: replace Abstract: Recent Vision-Language-Action (VLA) models for autonomous driving (AD) increasingly utilize chain-of-thought (CoT) supervision to enhance the reasoning capabilities of their Vision-Language Model (VLM) components, yet existing annotation pipelines commonly expose the teacher model to the logged ground-truth (GT) future trajectory.
The paper argues that current embodied vision‑language planning benchmarks favor linguistic next‑token prediction over physically grounded next‑state reasoning, leading models to rely on language priors rather than true causal dependencies. To address this, the authors introduce Causal‑Plan‑Bench, a diagnostic suite covering four causal dimensions, and Causal‑Plan‑1M, a million‑scale corpus of explicit causal reasoning traces extracted from egocentric videos. Extensive experiments show that existing models perform poorly on these tasks, while a new model trained with a tailored recipe—Causal Planner based on Qwen3‑VL‑8B—achieves significant gains, demonstrating the feasibility of physically grounded causal reasoning.
The paper introduces DriveMind, a large-scale driving Visual Question Answering corpus that aligns chain-of-thought reasoning with trajectory planning. Experiments with Vision‑Language Model agents show a causal disconnect: removing navigation priors significantly harms planning, while removing the chain-of-thought has little effect. The authors propose the Reasoning‑Planning Decoupling Hypothesis and present a training‑free probe to assess an agent’s reliance on priors.
CAR‑VLA is a Vision‑Language‑Action model for autonomous driving that jointly considers scene complexity and dynamic risk to determine reasoning depth, urgency, and focus. It maps four complexity‑risk categories to three reasoning modes—Fast Intuition, Slow Thinking, and Reflex Response—each tailored to different driving scenarios. The model is trained via progressive supervised learning and reinforcement learning, achieving competitive performance on NAVSIM and Navhard benchmarks and demonstrating risk‑aware reasoning in high‑risk scenarios.
arXiv:2606. 01810v1 Announce Type: new Abstract: Current benchmarks for embodied vision-language planning often favor linguistic next-token prediction over physically grounded next-state reasoning.