Researchers have developed ChatPlanner, a framework for personalized public transit routing using large language models. The system uses fine-tuned models to extract and interpret user preferences from natural language queries, integrating them into the routing algorithm. This approach allows for more accurate and relevant route suggestions compared to traditional planners. The study demonstrates that ChatPlanner can capture user conversationally expressed preferences, generating more route alternatives than existing systems. The framework is also computationally tractable, making it a viable solution for real-world applications. --- Why it matters: This matters because it addresses the challenge of capturing diverse user preferences in public transit routing, which can lead to more efficient and effective transportation systems. By leveraging natural language understanding, ChatPlanner has the potential to improve the travel experience for users with specific needs or preferences. Source: https://arxiv.org/abs/2606.15315