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

• URL: http://arxiv.org/abs/2607.14387v1
• Date: Wed, 15 Jul 2026 22:02:03 GMT
• Title: Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
• Abstract summary: We present Chat2Scenic, the first iterative retrieval-augmented framework to generate scenario scripts in specific language.<n>Chat2Scenic supports interactive scenario refinement and integrates Retrieval-augmented Generation (RAG) to ground scenario generation in regulatory knowledge and DSL syntax.<n>We propose an open benchmark for scenario generation comprising 123 scenarios from various regulations, including NHTSA and United Nations Vehicle Regulations.
• Score: 9.511162573483828
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Scenario Generation for Testing of Autonomous Driving Systems Using Real-World Failure Records [19.330267460084773]
  We propose a scenario generation pipeline using categorical and contextual information available from historical records in natural language format.<n>We successfully apply our method to generate a diverse set of scenarios for testing autonomous navigation on Metadrive simulator.
  arXiv  Detail & Related papers  (2026-06-30T04:56:25Z)
• ClawEnvKit: Automatic Environment Generation for Claw-Like Agents [85.29126619772153]
  We introduce ClawEnvKit, an autonomous generation pipeline capable of generating verified environments on demand.<n>ClawEnvKit comprises three modules: (1) a pipeline that extracts structured generation parameters from natural language input; (2) a generator that produces the task specification, tool interface, and scoring configuration; and (3) a validator that enforces feasibility, diversity, structural validity, and internal consistency.<n>We construct Auto-ClawEval, the first large-scale benchmark for claw-like agents, comprising 1,040 environments across 24 categories.
  arXiv  Detail & Related papers  (2026-04-20T17:36:49Z)
• Declarative Scenario-based Testing with RoadLogic [2.2107822884016404]
  We present RoadLogic that bridges declarative OS2 specifications and executable simulations.<n>Results show that RoadLogic consistently produces realistic, specification-satisfying simulations within minutes.
  arXiv  Detail & Related papers  (2026-03-10T10:11:09Z)
• iScript: A Domain-Adapted Large Language Model and Benchmark for Physical Design Tcl Script Generation [48.502477318243386]
  iScript is a domain-adapted Qwen3-8B model for Innovus Tcl script generation.<n>iScript shows higher pass@k scores than currently state-of-the-art LLMs on average.
  arXiv  Detail & Related papers  (2026-03-04T15:20:35Z)
• An LLM-driven Scenario Generation Pipeline Using an Extended Scenic DSL for Autonomous Driving Safety Validation [4.602386383455713]
  Real-world crash reports are valuable for scenario-based testing of autonomous driving systems.<n>Current methods cannot effectively translate this multimodal data into precise, executable simulation scenarios.<n>We propose a scalable and verifiable pipeline that uses a large language model and a probabilistic intermediate representation.
  arXiv  Detail & Related papers  (2026-02-24T07:44:26Z)
• Req2Road: A GenAI Pipeline for SDV Test Artifact Generation and On-Vehicle Execution [24.305511228249486]
  Large Language Models and Vision-Language Models are used to extract signals and behavioral logic.<n>The pipeline uses retrieval-augmented generation to preselect candidate VSS signals before mapping.<n>This paper is a feasibility and architectural demonstration of an end-to-end requirements-to-test pipeline for SDV subsystems.
  arXiv  Detail & Related papers  (2026-02-17T14:03:35Z)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)
• Text2Scenario: Text-Driven Scenario Generation for Autonomous Driving Test [15.601818101020996]
  Text2Scenario is a framework that autonomously generates simulation test scenarios that closely align with user specifications.<n>Result is an efficient and precise evaluation of diverse AD stacks void of the labor-intensive need for manual scenario configuration.
  arXiv  Detail & Related papers  (2025-03-04T07:20:25Z)
• 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)
• In-Context Learning for Few-Shot Dialogue State Tracking [55.91832381893181]
  We propose an in-context (IC) learning framework for few-shot dialogue state tracking (DST) A large pre-trained language model (LM) takes a test instance and a few annotated examples as input, and directly decodes the dialogue states without any parameter updates. This makes the LM more flexible and scalable compared to prior few-shot DST work when adapting to new domains and scenarios.
  arXiv  Detail & Related papers  (2022-03-16T11:58:24Z)
• proScript: Partially Ordered Scripts Generation via Pre-trained Language Models [49.03193243699244]
  We demonstrate for the first time that pre-trained neural language models (LMs) can be finetuned to generate high-quality scripts. We collected a large (6.4k), crowdsourced partially ordered scripts (named proScript) Our experiments show that our models perform well (e.g., F1=75.7 in task (i)), illustrating a new approach to overcoming previous barriers to script collection.
  arXiv  Detail & Related papers  (2021-04-16T17:35:10Z)

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.