# Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving

arXiv: https://arxiv.org/abs/2607.14387 · HTML: https://mlsanity.com/paper/2607.14387/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)
- End-to-end autonomous driving / [Large language models for driving](https://mlsanity.com/driving/large-language-models-for-driving/)

## Builds on (most cited first, 23 of 23)

- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective](https://mlsanity.com/paper/2202.02215/) (2022)
- [ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles](https://mlsanity.com/paper/2405.14062/) (2024)
- [Scenic: A Language for Scenario Specification and Scene Generation](https://mlsanity.com/paper/1809.09310/) (2018)
- [Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis](https://mlsanity.com/paper/2506.11526/) (2025)
- [ChatSUMO: Large Language Model for Automating Traffic Scenario Generation in Simulation of Urban MObility](https://mlsanity.com/paper/2409.09040/) (2024)
- [6-Layer Model for a Structured Description and Categorization of Urban Traffic and Environment](https://mlsanity.com/paper/2012.06319/) (2020)
- [Multimodal Large Language Model Driven Scenario Testing for Autonomous Vehicles](https://mlsanity.com/paper/2409.06450/) (2024)
- [Text2Scenario: Text-Driven Scenario Generation for Autonomous Driving Test](https://mlsanity.com/paper/2503.02911/) (2025)
- [Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Model](https://mlsanity.com/paper/2409.09575/) (2024)
- [Realistic Corner Case Generation for Autonomous Vehicles with Multimodal Large Language Model](https://mlsanity.com/paper/2412.00243/) (2024)
- [ScenicNL: Generating Probabilistic Scenario Programs from Natural Language](https://mlsanity.com/paper/2405.03709/) (2024)
- [LMM-enhanced Safety-Critical Scenario Generation for Autonomous Driving System Testing From Non-Accident Traffic Videos](https://mlsanity.com/paper/2406.10857/) (2024)
- [SoVAR: Building Generalizable Scenarios from Accident Reports for Autonomous Driving Testing](https://mlsanity.com/paper/2409.08081/) (2024)
- [LeGEND: A Top-Down Approach to Scenario Generation of Autonomous Driving Systems Assisted by Large Language Models](https://mlsanity.com/paper/2409.10066/) (2024)
- [1001 Ways of Scenario Generation for Testing of Self-driving Cars: A Survey](https://mlsanity.com/paper/2304.10850/) (2023)
- [From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios](https://mlsanity.com/paper/2502.02145/) (2025)
- [A new Taxonomy for Automated Driving: Structuring Applications based on their Operational Design Domain, Level of Automation and Automation Readiness](https://mlsanity.com/paper/2404.17044/) (2024)
- [Generating Traffic Scenarios via In-Context Learning to Learn Better Motion Planner](https://mlsanity.com/paper/2412.18086/) (2024)
- [NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving](https://mlsanity.com/paper/2509.25944/) (2025)
- [Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles](https://mlsanity.com/paper/2410.09829/) (2024)
- [LinguaSim: Interactive Multi-Vehicle Testing Scenario Generation via Natural Language Instruction Based on Large Language Models](https://mlsanity.com/paper/2510.08046/) (2025)
- [David vs. Goliath: A comparative study of different-sized LLMs for code generation in the domain of automotive scenario generation](https://mlsanity.com/paper/2510.14115/) (2025)

## Built on by (most cited first, 1 of 1)

- [PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving](https://mlsanity.com/paper/2609.08965/) (2026)

## Abstract (arXiv)

Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based testing, scenarios are defined as executable scripts. Yet automatically generating such scripts from regulatory descriptions remains an open challenge, and existing approaches face fundamental trade-offs. Retrieval-assemble methods achieve reasonable compilation rates but lack scalability, whereas retrieval-based full-script generation suffers from low compilation success rates. We present Chat2Scenic, the first iterative retrieval-augmented framework to generate scenario scripts in Domain Specific Language (DSL). Specifically, Chat2Scenic provides a chatbot interface that supports interactive scenario refinement and integrates Retrieval-augmented Generation (RAG) to ground scenario generation in regulatory knowledge and DSL syntax. Furthermore, we propose an open benchmark for scenario generation comprising 123 scenarios from various regulations, including NHTSA and United Nations Vehicle Regulations, as well as other sources. Extensive evaluation with State-of-the-Art (SOTA) Large Language Models (LLMs) demonstrates that Chat2Scenic achieves 76.42% Compilation Success Rate (CSR) and 58.17% Framework Accuracy (FA), outperforming existing methods (Retrieval Assemble with 30.08% CSR, 11.03% FA and Retrieval full script generation with 16.26% CSR, 10.86% FA). To facilitate future research, we release our code as open source at https://github.com/TUM-AVS/chat2scenic.