Tag
This paper introduces DiffTilt, a distributional framework that exponentially tilts a diffusion model-induced joint distribution over environments and executions to efficiently discover rare safety-critical failures in autonomous and cyber-physical systems, outperforming conditional sampling strategies on ARCH-COMP benchmarks and a new tractor-trailer benchmark.
This paper extends AssetOpsBench with a Smart Grid Transformer asset class and introduces ScenarioGeneratorAgent, a pipeline for synthetic industrial-agent scenario generation that achieves an 8x runtime improvement while maintaining scenario quality.
Chat2Scenic is an iterative RAG-based framework that generates executable scenario scripts in Domain Specific Language from regulatory descriptions for autonomous driving testing, achieving 76.42% compilation success rate and outperforming existing methods.
This paper proposes a decision-focused generative framework for correlated scenario generation in distributionally robust optimization for grid dispatch, optimizing scenarios based on downstream operational cost rather than forecast accuracy. It reduces operational cost by 0.80–2.02% compared to accuracy-oriented methods across different generative models.
This paper proposes a modular LLM-based pipeline that generates diverse test scenarios for autonomous driving systems using historical failure records (e.g., NHTSA crash data), enabling effective failure discovery within limited testing budgets.
This research paper proposes a transformer-based reinforcement learning framework to automatically generate safety-critical test scenarios for Unmanned Traffic Management (UTM) systems, achieving an 8× improvement in vulnerability discovery efficiency over expert-guided testing.
ScenePilot proposes a feasibility-guided, boundary-driven framework for generating safety-critical scenarios for autonomous driving, using constrained multi-objective reinforcement learning to produce physically valid yet failure-inducing scenarios.