arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.10294eess.SYcs.AIcs.SY
收藏

推理中的模拟(SiR):面向自主交通系统经验导向AI的概念框架

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

Wuping Xin

AI总结:

SiR通过将领域模拟器嵌入LLM推理循环,为自主交通系统提供经验导向的AI框架,提升策略验证与优化能力。

摘要:

大型语言模型(LLMs)通过链式思维(CoT)等技术提升了推理能力。然而,其推理主要停留在文本和假设层面,缺乏在复杂动态领域如交通中的经验基础。本文介绍了推理中的模拟(SiR),一种新颖的概念框架,将领域特定的模拟器直接嵌入LLM推理循环中。通过将中间推理步骤视为可执行的模拟实验,SiR将LLM推理从叙述可能性转变为可检验的假设-模拟-分析工作流程。我们讨论了应用,其中LLM可以提出智能交通系统(ITS)策略假设,通过模型上下文协议(MCP)调用交通模拟器,在不同需求模式下评估结果,并通过验证和聚合优化策略。尽管实现该框架是我们的持续工作,本文主要建立了概念基础,讨论了API粒度等设计考虑,并概述了SiR作为交互式交通数字孪生基石的愿景。我们认为SiR是迈向可信、经验验证的自主交通系统AI的关键一步。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑