AI RESEARCH

nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving

arXiv CS.CV

ArXi:2605.31572v1 Announce Type: new Reasoning is essential for autonomous driving (AD) in long-tail scenarios, where vehicles must apply commonsense knowledge, understand spatial relations, infer agent interactions, and make safe decisions. However, existing AD datasets and benchmarks mainly target perception, prediction, or planning, and provide limited supervision for reasoning over realistic long-tail driving scenes. We