Learning from Risk: LLM-Guided Generation of Safety-Critical Scenarios with Prior Knowledge

• URL: http://arxiv.org/abs/2511.20726v1
• Date: Tue, 25 Nov 2025 09:53:09 GMT
• Title: Learning from Risk: LLM-Guided Generation of Safety-Critical Scenarios with Prior Knowledge
• Authors: Yuhang Wang, Heye Huang, Zhenhua Xu, Kailai Sun, Baoshen Guo, Jinhua Zhao,
• Abstract summary: This paper presents a high-fidelity scenario generation framework that integrates a conditional variational autoencoder (CVAE) with a large language model (LLM)<n>Our framework substantially increases the coverage of high-risk and long-tail events, improves consistency between simulated and real-world traffic distributions, and exposes autonomous driving systems to interactions that are significantly more challenging than those produced by existing rule- or data-driven methods.
• Score: 25.50999678115561
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous driving faces critical challenges in rare long-tail events and complex multi-agent interactions, which are scarce in real-world data yet essential for robust safety validation. This paper presents a high-fidelity scenario generation framework that integrates a conditional variational autoencoder (CVAE) with a large language model (LLM). The CVAE encodes historical trajectories and map information from large-scale naturalistic datasets to learn latent traffic structures, enabling the generation of physically consistent base scenarios. Building on this, the LLM acts as an adversarial reasoning engine, parsing unstructured scene descriptions into domain-specific loss functions and dynamically guiding scenario generation across varying risk levels. This knowledge-driven optimization balances realism with controllability, ensuring that generated scenarios remain both plausible and risk-sensitive. Extensive experiments in CARLA and SMARTS demonstrate that our framework substantially increases the coverage of high-risk and long-tail events, improves consistency between simulated and real-world traffic distributions, and exposes autonomous driving systems to interactions that are significantly more challenging than those produced by existing rule- or data-driven methods. These results establish a new pathway for safety validation, enabling principled stress-testing of autonomous systems under rare but consequential events.

Related papers

• ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation [72.78362530982109]
  ARTIS, Agentic Risk-Aware Test-Time Scaling via Iterative Simulation, is a framework that decouples exploration from commitment.<n>We show that naive LLM-based simulators struggle to capture rare but high-impact failure modes.<n>We introduce a risk-aware tool simulator that emphasizes fidelity on failure-inducing actions.
  arXiv  Detail & Related papers  (2026-02-02T06:33:22Z)
• Controllable risk scenario generation from human crash data for autonomous vehicle testing [13.3074428571403]
  Controllable Risk Agent Generation (CRAG) is a framework designed to unify the modeling of dominant nominal behaviors and rare safety-critical behaviors.<n>CRAG constructs a structured latent space that disentangles normal and risk-related behaviors, enabling efficient use of limited crash data.
  arXiv  Detail & Related papers  (2025-11-27T04:53:18Z)
• AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models [75.214287449744]
  We introduce a framework for post-training policy refinement built around an Impartial World Model.<n>Our primary contribution is to teach this model to be honest about danger.<n>We demonstrate through extensive experiments, that our model significantly outperforms baselines in predicting failures.
  arXiv  Detail & Related papers  (2025-11-25T13:57:24Z)
• A Trajectory Generator for High-Density Traffic and Diverse Agent-Interaction Scenarios [37.38654549322757]
  We propose a novel trajectory generation framework that simultaneously enhances scenarios density and enriches behavioral diversity.<n>Our method significantly improves both agent density and behavior diversity, while preserving motion realism and scenario-level safety.<n>Our synthetic data also benefits downstream trajectory prediction models and enhances performance in challenging high-density scenarios.
  arXiv  Detail & Related papers  (2025-10-03T00:12:18Z)
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator [77.86600052899156]
  Large Language Model (LLM)-based agents are increasingly deployed in real-world applications.<n>We propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation.<n>We show that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks.
  arXiv  Detail & Related papers  (2025-05-23T10:56:06Z)
• RADE: Learning Risk-Adjustable Driving Environment via Multi-Agent Conditional Diffusion [17.46462636610847]
  Risk- Driving Environment (RADE) is a simulation framework that generates statistically realistic and risk-adjustable traffic scenes.<n>RADE learns risk-conditioned behaviors directly from data, preserving naturalistic multi-agent interactions with controllable risk levels.<n>We validate RADE on the real-world rounD dataset, demonstrating that it preserves statistical realism across varying risk levels.
  arXiv  Detail & Related papers  (2025-05-06T04:41:20Z)
• RiskNet: Interaction-Aware Risk Forecasting for Autonomous Driving in Long-Tail Scenarios [6.024186631622774]
  RiskNet is an interaction-aware risk forecasting framework for autonomous vehicles.<n>It integrates deterministic risk modeling with probabilistic behavior prediction for comprehensive risk assessment.<n>It supports real-time, scenario-adaptive risk forecasting and demonstrates strong generalization across uncertain driving environments.
  arXiv  Detail & Related papers  (2025-04-22T02:36:54Z)
• SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models [63.71984266104757]
  We propose SafeAuto, a framework that enhances MLLM-based autonomous driving by incorporating both unstructured and structured knowledge.<n>To explicitly integrate safety knowledge, we develop a reasoning component that translates traffic rules into first-order logic.<n>Our Multimodal Retrieval-Augmented Generation model leverages video, control signals, and environmental attributes to learn from past driving experiences.
  arXiv  Detail & Related papers  (2025-02-28T21:53:47Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios [58.62407014256686]
  RealGen is a novel retrieval-based in-context learning framework for traffic scenario generation. RealGen synthesizes new scenarios by combining behaviors from multiple retrieved examples in a gradient-free way. This in-context learning framework endows versatile generative capabilities, including the ability to edit scenarios.
  arXiv  Detail & Related papers  (2023-12-19T23:11:06Z)
• Empowering Autonomous Driving with Large Language Models: A Safety Perspective [82.90376711290808]
  This paper explores the integration of Large Language Models (LLMs) into Autonomous Driving systems. LLMs are intelligent decision-makers in behavioral planning, augmented with a safety verifier shield for contextual safety learning. We present two key studies in a simulated environment: an adaptive LLM-conditioned Model Predictive Control (MPC) and an LLM-enabled interactive behavior planning scheme with a state machine.
  arXiv  Detail & Related papers  (2023-11-28T03:13:09Z)
• Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving [33.672722472758636]
  offline Reinforcement Learning(RL) approaches exhibit notable efficacy in addressing sequential decision-making problems from offline datasets. We introduce the saFety-aware strUctured Scenario representatION ( Fusion) to facilitate the learning of a generalizable end-to-end driving policy. Empirical evidence in various driving scenarios attests that Fusion significantly enhances the safety and generalizability of autonomous driving agents.
  arXiv  Detail & Related papers  (2023-10-31T18:21:24Z)
• CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation [34.45216283597149]
  We propose a flow-based generative framework, Causal Autoregressive Flow (CausalAF) CausalAF encourages the generative model to uncover and follow the causal relationship among generated objects. We show that using generated scenarios as additional training samples empirically improves the robustness of autonomous driving algorithms.
  arXiv  Detail & Related papers  (2021-10-26T18:07:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.