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

Hugging Face Daily Papers Papers
autonomous-driving scenario-generation retrieval-augmented-generation dsl benchmark llm open-source

Summary

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.

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.
Original Article
View Cached Full Text

Cached at: 07/20/26, 09:41 AM

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

Source: https://huggingface.co/papers/2607.14387

Abstract

Validatingautonomousdrivingsystemsrequiresdiverse,regulation-complianttestscenarios.Insimulation-basedtesting,scenariosaredefinedasexecutablescripts.Yetautomaticallygeneratingsuchscriptsfromregulatorydescriptionsremainsanopenchallenge,andexistingapproachesfacefundamentaltrade-offs.Retrieval-assemblemethodsachievereasonablecompilationratesbutlackscalability,whereasretrieval-basedfull-scriptgenerationsuffersfromlowcompilationsuccessrates.WepresentChat2Scenic,thefirstiterativeretrieval-augmentedframeworktogeneratescenarioscriptsinDomainSpecificLanguage(DSL).Specifically,Chat2ScenicprovidesachatbotinterfacethatsupportsinteractivescenariorefinementandintegratesRetrieval-augmentedGeneration(RAG)togroundscenariogenerationinregulatoryknowledgeandDSLsyntax.Furthermore,weproposeanopenbenchmarkforscenariogenerationcomprising123scenariosfromvariousregulations,includingNHTSAandUnitedNationsVehicleRegulations,aswellasothersources.ExtensiveevaluationwithState-of-the-Art(SOTA)LargeLanguageModels(LLMs)demonstratesthatChat2Scenicachieves76.42%CompilationSuccessRate(CSR)and58.17%FrameworkAccuracy(FA),outperformingexistingmethods(RetrievalAssemblewith30.08%CSR,11.03%FAandRetrievalfullscriptgenerationwith16.26%CSR,10.86%FA).Tofacilitatefutureresearch,wereleaseourcodeasopensourceathttps://github.com/TUM-AVS/chat2scenic.

View arXiv pageView PDFProject pageGitHub7Add to collection

Get this paper in your agent:

hf papers read 2607\.14387

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.14387 in a model README.md to link it from this page.

Datasets citing this paper1

#### chat2scenic/Chat2Scenic Updated3 days ago • 63 • 1

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.14387 in a Space README.md to link it from this page.

Collections including this paper2

Similar Articles

AutoMine Solution for AV2 2026 Scenario Mining Challenge

arXiv cs.AI

AutoMine is a robust self-refining scenario mining method using LLMs and VLMs to mine high-value scenarios from autonomous driving logs, achieving top scores in the Argoverse 2 Scenario Mining Competition at CVPR 2026.