Claude Code-Driving Scenario Mining for the Argoverse 2 Challenge
Researchers have developed a novel four-stage pipeline for the CVPR 2026 Argoverse 2 Scenario Mining Challenge. This system leverages a Claude Code agent, powered by GLM 5.1, for autonomous code generation. It then refines training data through iterative screening and semantic code review, also using Claude Code. Finally, Qwen3-VL is employed for scene-level verification to ensure accuracy. AI
IMPACT Demonstrates novel pipeline for autonomous driving scenario mining using LLMs.