SOURCE-LINKED INTELLIGENCE

AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

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. We introduce AnchorReasoning, a visually grounded reasoning dataset built on WOD-E2E, containing 416,119 annotated frames and 395,379 decision-critical elements across four major categories and 19 fine-grained types. Each frame is organized as a visually grounded chain-of-thought (VG-CoT) that links decision-critical element identification and localization, element attrib

Read original source ↗ Open in workspace

recordType

paper

region

Global