超越最短路径：具有语义上下文的智能体车辆路径规划
Beyond Shortest Path: Agentic Vehicular Routing with Semantic Context
AI总结：
本文提出PAVe系统，将多目标Dijkstra算法与LLM语义推理相结合，利用城市POI缓存理解用户复杂意图，实现个性化车辆路径规划，初始路线选择准确率超过88%。
摘要：
传统车辆路径规划系统能够高效优化时间或距离等单一指标，而在考虑多个指标时，则需要更多处理流程来进行优化。然而，它们缺乏解读和整合人类驾驶员复杂、语义化且动态的上下文信息的能力，例如多步骤任务、情境约束或紧急需求。本文提出并评估了PAVe（个性化智能体车辆路径规划），这是一种混合式智能体助手，旨在通过上下文推理来增强经典路径搜索算法。我们的方法采用一个大语言模型（LLM）智能体，该智能体在多目标（时间、CO2）Dijkstra算法生成的候选路线集合上进行操作。该智能体通过利用预先处理的城市兴趣点（POIs）地理空间缓存，根据用户提供的任务、偏好和规避规则来评估这些候选方案。在一个由真实城市场景构成的基准测试中，PAVe成功将复杂的用户意图转化为适当的路线修改，在使用本地模型时，其初始路线选择的准确率超过88%。我们得出结论：将经典路径规划算法与基于LLM的语义推理层相结合，是一种稳健且有效的方法，可用于创建个性化、自适应且可扩展的城市出行优化解决方案。
英文摘要：
Traditional vehicle routing systems efficiently optimize singular metrics like time or distance, and when considering multiple metrics, they need more processes to optimize . However, they lack the capability to interpret and integrate the complex, semantic, and dynamic contexts of human drivers, such as multi-step tasks, situational constraints, or urgent needs. This paper introduces and evaluates PAVe (Personalized Agentic Vehicular Routing), a hybrid agentic assistant designed to augment classical pathfinding algorithms with contextual reasoning. Our approach employs a Large Language Model (LLM) agent that operates on a candidate set of routes generated by a multi-objective (time, CO2) Dijkstra algorithm. The agent evaluates these options against user-provided tasks, preferences, and avoidance rules by leveraging a pre-processed geospatial cache of urban Points of Interest (POIs). In a benchmark of realistic urban scenarios, PAVe successfully used complex user intent into appropriate route modifications, achieving over 88% accuracy in its initial route selections with a local model. We conclude that combining classical routing algorithms with an LLM-based semantic reasoning layer is a robust and effective approach for creating personalized, adaptive, and scalable solutions for urban mobility optimization.
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。
