让大模型在交通决策中边推理边仿真，提升自动驾驶系统的可信度。
Simulation-in-the-Reasoning (SiR): A Conceptual Framework for Empirically Grounded AI in Autonomous Transportation
- 把交通仿真器嵌入大模型推理流程，每步思考都可执行验证。
- 通过模拟不同交通需求，优化智能交通策略并迭代改进。
- 适合研究自动驾驶与数字孪生的学者，推动实证型AI发展。
大型语言模型（LLMs）通过思维链（CoT）等技术提升了推理能力，但在复杂动态领域如交通系统中，其推理仍以文本为主、缺乏实证支撑。本文提出仿真-推理框架（SiR），将领域专用仿真器直接嵌入LLM推理循环中。通过将中间推理步骤视为可执行的仿真实验，SiR使模型推理从叙事合理性转变为可检验的‘假设-仿真-分析’流程。我们探讨了应用场景：大模型可生成智能交通系统（ITS）策略假设，通过模型上下文协议（MCP）调用交通仿真器，评估不同需求模式下的结果，并基于验证与聚合不断优化策略。尽管框架实现仍在进行中，本文主要建立概念基础，讨论接口粒度等设计考量，并展望SiR作为交互式交通数字孪生核心的愿景。我们认为，SiR是迈向可信赖、实证验证的自动驾驶系统人工智能的关键一步。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have advanced reasoning through techniques like Chain-of-Thought (CoT). However, their reasoning largely re-mains textual and hypothetical, lacking empirical grounding in complex, dynamic domains like transportation. This paper introduces Simulation-in-the-Reasoning (SiR), a novel conceptual framework that embeds domain-specific simulators directly into the LLM reasoning loop. By treating intermediate reasoning steps as executable simulation experiments, SiR transforms LLM reasoning from narrative plausibility into a falsifiable, hypothesis-simulate-analyze workflow. We discuss applications, where LLM can formulate Intelligent Transport System (ITS) strategy hypotheses, invoke a traffic simulator via the Model Context Protocol (MCP), evaluate results under different demand patterns, and refine strategies through verification and aggregation. While implementing the framework is part of our ongoing work, this paper primarily establishes the conceptual foundation, discusses design considerations like API granularity, and outlines the vision of SiR as a cornerstone for interactive transportation digital twins. We argue that SiR represents a critical step towards trustworthy, empirically-validated AI for autonomous transportation systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。