Saved in:
Bibliographic Details
Main Authors: Poddubnyy, Konstantin, Vozniak, Igor, Burmistrov, Ivan, Lipp, Nils, Hovhannisyan, Davit, Mueller, Christian, Slusallek, Philipp
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.14743
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918312663842816
author Poddubnyy, Konstantin
Vozniak, Igor
Burmistrov, Ivan
Lipp, Nils
Hovhannisyan, Davit
Mueller, Christian
Slusallek, Philipp
author_facet Poddubnyy, Konstantin
Vozniak, Igor
Burmistrov, Ivan
Lipp, Nils
Hovhannisyan, Davit
Mueller, Christian
Slusallek, Philipp
contents The effectiveness of collision-free trajectory planners depends on the quality and diversity of training data, especially for rare scenarios. A widely used approach to improve dataset diversity involves generating realistic synthetic traffic scenarios. However, producing such scenarios remains difficult due to the precision required when scripting them manually or generating them in a single pass. Natural language offers a flexible way to describe scenarios, but existing text-to-simulation pipelines often rely on static snippet retrieval, limited grammar, single-pass decoding, or lack robust executability checks. Moreover, they depend heavily on constrained LLM prompting with minimal post-processing. To address these limitations, we introduce ARISE - Adaptive Refinement and Iterative Scenario Engineering, a multi-stage tool that converts natural language prompts into executable Scenic scripts through iterative LLM-guided refinement. After each generation, ARISE tests script executability in simulation software, feeding structured diagnostics back to the LLM until both syntactic and functional requirements are met. This process significantly reduces the need for manual intervention. Through extensive evaluation, ARISE outperforms the baseline in generating semantically accurate and executable traffic scenarios with greater reliability and robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14743
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ARISE -- Adaptive Refinement and Iterative Scenario Engineering
Poddubnyy, Konstantin
Vozniak, Igor
Burmistrov, Ivan
Lipp, Nils
Hovhannisyan, Davit
Mueller, Christian
Slusallek, Philipp
Software Engineering
The effectiveness of collision-free trajectory planners depends on the quality and diversity of training data, especially for rare scenarios. A widely used approach to improve dataset diversity involves generating realistic synthetic traffic scenarios. However, producing such scenarios remains difficult due to the precision required when scripting them manually or generating them in a single pass. Natural language offers a flexible way to describe scenarios, but existing text-to-simulation pipelines often rely on static snippet retrieval, limited grammar, single-pass decoding, or lack robust executability checks. Moreover, they depend heavily on constrained LLM prompting with minimal post-processing. To address these limitations, we introduce ARISE - Adaptive Refinement and Iterative Scenario Engineering, a multi-stage tool that converts natural language prompts into executable Scenic scripts through iterative LLM-guided refinement. After each generation, ARISE tests script executability in simulation software, feeding structured diagnostics back to the LLM until both syntactic and functional requirements are met. This process significantly reduces the need for manual intervention. Through extensive evaluation, ARISE outperforms the baseline in generating semantically accurate and executable traffic scenarios with greater reliability and robustness.
title ARISE -- Adaptive Refinement and Iterative Scenario Engineering
topic Software Engineering
url https://arxiv.org/abs/2601.14743