Simulation-in-the-Reasoning (SiR): A Conceptual Framework for Empirically Grounded AI in Autonomous Transportation

Researchers propose Simulation-in-the-Reasoning (SiR), a framework that embeds domain-specific simulators into Large Language Model reasoning processes for autonomous transportation systems. The approach transforms LLM reasoning from hypothetical text generation into empirically-grounded, falsifiable hypothesis testing through executable simulation experiments.

• →SiR framework integrates traffic simulators directly into LLM reasoning loops to ground AI decision-making in empirical data.
• →The approach enables LLMs to formulate transportation strategy hypotheses, test them via simulation, and refine strategies based on results.
• →SiR transforms LLM reasoning from narrative plausibility into a falsifiable hypothesis-simulate-analyze workflow.
• →The framework aims to serve as a foundation for interactive transportation digital twins and trustworthy autonomous systems.
• →Implementation remains ongoing work, with the paper focusing on establishing conceptual foundations and design considerations.