Skip to content
Search
paperSeptember 2026Unreviewed

PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving

Yuan Gao, Sebastian Müller, Mattia Piccinini, Marc Kaufeld, Yuchen Zhang, Finn Rasmus Schäfer, Qunying Song, Johannes Betz

View resourcePDF

Abstract

Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving Systems (ADSs), but it remains a fragmented modular pipeline in which scenario generation, retrieval, modification, ADS execution, and results analysis are performed by separate tools with little interaction. Large Language Model (LLM) agents have shown promise across ADS sub-systems such as perception, planning, and control. However, no prior work

Categories

Agentic Threats

Cite

@misc{gao2026plannerforge,
  title = {{PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving}},
  author = {Yuan Gao and Sebastian Müller and Mattia Piccinini and Marc Kaufeld and Yuchen Zhang and Finn Rasmus Schäfer and Qunying Song and Johannes Betz},
  year = {2026},
  month = sep,
  eprint = {2609.08965},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.08965}
}