Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles
Jiangfan Liu, Yongkang Guo, Fangzhi Zhong, Tianyuan Zhang, Zonglei Jing, Siyuan Liang, Jiakai Wang, Mingchuan Zhang
Abstract
The generation of safety-critical scenarios in simulation has become increasingly crucial for safety evaluation in autonomous vehicles (AV) prior to road deployment in society. However, current approaches largely rely on predefined threat patterns or rule-based strategies, which limit their ability to expose diverse and unforeseen failure modes. To overcome these, we propose ScenGE, a framework that can generate plentiful safety-critical scenarios by reasoning novel adversarial cases and then amplifying them with complex traffic flows. Given a simple prompt of a benign scene, it first performs Meta-Scenario Generation, where a large language model (LLM), grounded in structured driving knowledge (e.g., traffic regulations, real-world accident records), infers an adversarial agent whose behavior poses a threat that is both plausible and deliberately challenging. This meta-scenario is then specified in executable code for precise in-simulator control. Subsequently, Complex Scenario Evolution uses background vehicles to amplify the core threat introduced by Meta-Scenario. It builds an adversarial collaborator graph to identify key agent trajectories for optimization. These perturbations are designed to simultaneously reduce the ego vehicle
BibTeX
@inproceedings{aaai2026_adversarialgener,
title = {Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles},
author = {Jiangfan Liu and Yongkang Guo and Fangzhi Zhong and Tianyuan Zhang and Zonglei Jing and Siyuan Liang and Jiakai Wang and Mingchuan Zhang and Aishan Liu and Xianglong Liu},
booktitle = {AAAI 2026},
year = {2026}
}