TourPlanner: 一种基于约束门控强化学习的竞争共识框架用于旅行规划
TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning
AI总结：
TourPlanner通过多路径推理和约束门控强化学习，解决旅行规划中候选点修剪、探索能力限制和约束优化难题，实现更高效的行程生成。
摘要：
旅行规划是一个复杂的决策过程，需要综合多方面的信息来构建行程。然而，现有的旅行规划方法面临几个挑战：（1）在保持高召回率的同时修剪兴趣点（POIs）的候选点；（2）单一推理路径限制了在可行解空间中的探索能力；（3）同时优化硬约束和软约束仍是一个重大困难。为了解决这些挑战，我们提出了TourPlanner，一个具有多路径推理和约束门控强化学习的综合性框架。具体来说，我们首先引入了个性化召回和空间优化（PReSO）工作流，以构建空间感知的候选POIs集合。随后，我们提出了竞争共识链式思维（CCoT），一种多路径推理范式，它提高了探索可行解空间的能力。为了进一步细化计划，我们将基于sigmoid的门控机制整合到强化学习阶段，该机制在满足硬约束之后动态优先满足软约束。在旅行规划基准上的实验结果表明，TourPlanner实现了最先进的性能，显著超过了现有方法在可行性和用户偏好对齐方面的表现。
英文摘要：
Travel planning is a sophisticated decision-making process that requires synthesizing multifaceted information to construct itineraries. However, existing travel planning approaches face several challenges: (1) Pruning candidate points of interest (POIs) while maintaining a high recall rate; (2) A single reasoning path restricts the exploration capability within the feasible solution space for travel planning; (3) Simultaneously optimizing hard constraints and soft constraints remains a significant difficulty. To address these challenges, we propose TourPlanner, a comprehensive framework featuring multi-path reasoning and constraint-gated reinforcement learning. Specifically, we first introduce a Personalized Recall and Spatial Optimization (PReSO) workflow to construct spatially-aware candidate POIs' set. Subsequently, we propose Competitive consensus Chain-of-Thought (CCoT), a multi-path reasoning paradigm that improves the ability of exploring the feasible solution space. To further refine the plan, we integrate a sigmoid-based gating mechanism into the reinforcement learning stage, which dynamically prioritizes soft-constraint satisfaction only after hard constraints are met. Experimental results on travel planning benchmarks demonstrate that TourPlanner achieves state-of-the-art performance, significantly surpassing existing methods in both feasibility and user-preference alignment.
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。
