Agentic AI for Trip Planning Optimization Application

TL;DR

This paper introduces an agentic AI framework for trip planning that dynamically refines routes by coordinating specialized agents, significantly improving optimization accuracy over existing methods.

Contribution

The paper presents a novel agentic AI system with an orchestration mechanism and a new dataset for trip planning, enabling more effective optimization and evaluation.

Findings

Achieves 77.4% accuracy on the TOP Benchmark

Outperforms single-agent and multi-agent baselines

Demonstrates the effectiveness of orchestrated agentic reasoning

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. 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. 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. 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.