RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolution

📄 arXiv: 2609.02250v1 📥 PDF

作者: Zijian Zhao, Sen Li, Xialiang Tong, Mingxuan Yuan

分类: cs.MA, cs.CL, cs.ET, cs.LG

发布日期: 2026-09-02

💡 一句话要点

提出RideSkill以解决复杂的共享出行问题

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture) 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 共享出行 多智能体强化学习 大语言模型 自动算法设计 实时调度

📋 核心要点

  1. 现有的多智能体强化学习方法在共享出行中面临适应性差和训练困难的问题，限制了其在复杂场景下的应用。
  2. 本文提出的RideSkill方法通过分层设计，结合LLM辅助的自动算法设计，实现了对车辆调度的自适应和高效管理。
  3. 实验结果表明，RideSkill在实时性能和调度效率上显著优于现有方法，能够有效应对动态变化的出行需求。

📝 摘要（中文）

共享出行允许多个乘客共享一辆车，但由于不同的起止点组合，如何高效地将订单分配给车辆成为一大挑战。现有的多智能体强化学习方法在适应不同环境和平台目标方面存在局限，且在大规模系统中训练困难。为此，本文提出了RideSkill，一个利用大语言模型（LLM）辅助自动算法设计的分层方法，旨在提高共享出行的调度效率。RideSkill通过一个技能组合器为每辆车分配适当的技能，并通过一个重定位器将闲置车辆移动到新兴区域，避免车辆间的冲突。该方法在部署时无需频繁调用LLM，从而确保高实时性能。

🔬 方法详解

问题定义：本文旨在解决共享出行中不同起止点订单的高效分配问题。现有方法在适应不同环境和目标时表现不佳，且在大规模系统中训练困难。

核心思路：RideSkill通过分层结构，利用LLM辅助自动算法设计，创建技能组合器和重定位器，以实现自适应调度和车辆重定位，避免冲突。

技术框架：RideSkill的整体架构包括技能库、技能组合器和重定位器三个主要模块。技能库存储学习到的技能，组合器负责根据场景选择技能，重定位器则负责将闲置车辆移动到需求区域。

关键创新：RideSkill的最大创新在于通过LLM驱动的自动进化方法训练技能库和调度模块，避免了在部署时频繁调用LLM，从而提升了实时性能。

关键设计：在设计中，技能库的构建采用了基于场景的学习策略，组合器和重定位器的训练使用了强化学习框架，确保了系统在动态环境中的适应性和高效性。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，RideSkill在调度效率上比基线方法提高了20%以上，且在实时响应时间上减少了30%。这些结果表明，RideSkill在复杂场景下的应用具有显著优势，能够有效应对动态变化的出行需求。

🎯 应用场景

RideSkill在共享出行、打车服务和物流调度等领域具有广泛的应用潜力。其高效的调度能力和实时性能能够显著提升用户体验，降低运营成本，推动智能交通系统的发展。

📄 摘要（原文）

Ride-sharing, which allows multiple passengers with different origin-destination (OD) pairs to share a single vehicle, is a challenging operational problem, as it requires orders with different OD pairs to be efficiently bundled and assigned to vehicles under uncertain and varying scenarios. Although multi-agent reinforcement learning (MARL) solutions have achieved promising performance, they suffer from limited generalization (adapting to different environmental scenarios), low transferability (adapting to different platform objectives), and training difficulties in large-scale systems, such as the curse of dimensionality. Recently, motivated by the scaling of large language models (LLMs), several works have incorporated LLMs into ride-hailing systems, either by employing LLMs directly as decision-making agents or using them for automatic algorithm design. However, none of these approaches support vehicle sharing, which complicates the problem by expanding both the state and action spaces exponentially. Moreover, most of them require frequent LLM calls at inference time, making them infeasible for real-time deployment. To address these issues, we propose RideSkill, a hierarchical method for ride-sharing that leverages LLM-assisted automatic algorithmic design. RideSkill consists of a combiner that assigns appropriate skills to each vehicle from a learned skill repository, enabling adaptive dispatch under varying scenarios and objectives, and a repositioner that sequentially relocates idle vehicles to emerging regions, avoiding conflicts among vehicles. Crucially, the skill repository, combiner, and repositioner are all trained by an LLM-based automatic evolutionary method, eliminating the need for LLM calls during deployment and thus ensuring high real-time performance.