What Will Happen Next: Large Models-Driven Deduction for Emergency Instances
Not on the map. Why?
Abstract (arXiv)
Traditional simulation methods reproduce occurred emergency instances through presetting to assist people in risk assessment and emergency decision-making. However, due to the lack of randomness and diversity, existing simulation systems struggle to fully explore the potential risk as emergency instances are scarce. In contrast, Large Models (LMs) can dynamically adjust generation strategies to introduce controllable randomness, while also possessing extensive prior knowledge and cross-domain knowledge transfer capabilities. Inspired by it, we propose the LMs-driven World Line Divergence System (WLDS), which enables diversified visualization and deduction of emergency instances in different domains. WLDS leverages LMs to deduce emergency instances in various development directions, and introduces the factual calibration and logical calibration mechanism to ensure factual accuracy and logical rigor during the deduction process. The interactive module can independently select deduction directions to avoid potential hallucinations that are difficult for the system to identify. Furthermore, by introducing the visualization module, WLDS forms simulation and deduction that combine text and images, which enhances interpretability. Extensive experiments conducted on the proposed Emergency Instances Deduction (EID) benchmark dataset demonstrate that WLDS achieves high-precision and high-fidelity simulation and deduction of emergency instances in multiple specific domains. Relevant experiments further demonstrate that WLDS can generate more emergency instances deduction data for users and provide support for better decision-making in similar emergency instances in the future.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 55 references that are in the map. First posted on arXiv 9 May 2026.
Builds on
19 of 55 references.
References · 19
- 2023A Survey of Large Language Modelscited by 2,537
- 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
- 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
- 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
- 2024ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehiclescited by 92
- 2024LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoningcited by 63
- 2017Ontology based Scene Creation for the Development of Automated Vehiclescited by 40
- 2024ChatSUMO: Large Language Model for Automating Traffic Scenario Generation in Simulation of Urban MObilitycited by 34
- 2023HAP: Structure-Aware Masked Image Modeling for Human-Centric Perceptioncited by 33
- 2021Domain-Specific Bias Filtering for Single Labeled Domain Generalizationcited by 18
- 2021Collaborative Semantic Aggregation and Calibration for Federated Domain Generalizationcited by 16
- 2023Safety-Critical Scenario Generation Via Reinforcement Learning Based Editingcited by 16
7 more
- 2022Label-Efficient Domain Generalization via Collaborative Exploration and Generalizationcited by 15
- 2024Improving Large Models with Small models: Lower Costs and Better Performancecited by 14
- 2023Interaction-aware Traffic Prediction and Scenario-based Model Predictive Control for Autonomous Vehicles on Highwayscited by 3
- 2025When Digital Twins Meet Large Language Models: Realistic, Interactive, and Editable Simulation for Autonomous Drivingcited by 3
- 2024Planning by Simulation: Motion Planning with Learning-based Parallel Scenario Prediction for Autonomous Drivingcited by 2
- 2025SACA: A Scenario-Aware Collision Avoidance Framework for Autonomous Vehicles Integrating LLMs-Driven Reasoningcited by 2
- 2025InclusiViz: Visual Analytics of Human Mobility Data for Understanding and Mitigating Urban Segregationcited by 1
Built on by
Not cited yet.