ARISE -- Adaptive Refinement and Iterative Scenario Engineering

TL;DR

ARISE is a multi-stage, LLM-guided system that iteratively refines natural language prompts into executable traffic scenarios, improving diversity, accuracy, and robustness for collision-free trajectory training.

Contribution

It introduces an iterative refinement process that enhances scenario generation from natural language, overcoming limitations of static and single-pass methods.

Findings

ARISE produces more accurate and executable scenarios.

The iterative process reduces manual intervention.

It outperforms baseline methods in scenario quality.

Abstract

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.