Agentic AI for Trip Planning Optimization Application
Agentic AI for Trip Planning Optimization Application
用于行程规划优化的智能体 AI 应用
Abstract: Trip planning for intelligent vehicles increasingly requires selecting optimal routes rather than merely producing feasible itineraries, as interacting factors such as travel time, energy consumption, and traffic conditions directly affect plan quality. 摘要： 智能车辆的行程规划日益要求选择最优路线，而不仅仅是生成可行的行程方案，因为旅行时间、能耗和交通状况等相互作用的因素直接影响着规划的质量。
Yet existing systems are largely designed for feasibility-oriented planning, and current benchmarks provide only reference answers without ground truth, preventing objective evaluation of optimization performance. 然而，现有的系统大多是为“可行性导向”的规划而设计的，且当前的基准测试仅提供参考答案而缺乏真实标准（ground truth），这阻碍了对优化性能的客观评估。
In our paper, we address these limitations with an agentic AI framework that enables dynamic refinement through an orchestration agent coordinating specialized agents for traffic, charging, and points of interest, and with the Trip-planning Optimization Problems Dataset, which supplies definitive optimal solutions and category-level task structure for fine-grained analysis. 在本文中，我们通过一个智能体 AI 框架解决了这些局限性。该框架通过一个编排智能体（orchestration agent）来协调负责交通、充电和兴趣点的专业智能体，从而实现动态优化；同时，我们提出了“行程规划优化问题数据集”（Trip-planning Optimization Problems Dataset），该数据集提供了明确的最优解和类别级的任务结构，以进行细粒度的分析。
Experiments show that our system achieves 77.4% accuracy on the TOP Benchmark, significantly outperforming single-agent and workflow-based multi-agent baselines, demonstrating the importance of orchestrated agentic reasoning for robust trip planning optimization. 实验表明，我们的系统在 TOP 基准测试中达到了 77.4% 的准确率，显著优于单智能体和基于工作流的多智能体基准模型，证明了编排式智能体推理对于稳健的行程规划优化的重要性。
Paper Details:
- Authors: Tiejin Chen, Ahmadreza Moradipari, Kyungtae Han, Hua Wei, Nejib Ammar
- arXiv ID: 2605.00276
- Subject: Artificial Intelligence (cs.AI)
- Submission Date: 30 Apr 2026
论文详情：
- 作者： Tiejin Chen, Ahmadreza Moradipari, Kyungtae Han, Hua Wei, Nejib Ammar
- arXiv ID： 2605.00276
- 学科： 人工智能 (cs.AI)
- 提交日期： 2026年4月30日