解决长程旅行规划中预算与多样性约束难题，实现高效并行决策。
HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel
- 分层架构：协调器统筹资源分配，执行器并行规划每日行程。
- 预算与唯一性约束通过交易监控强制执行，提升计划合规性。
- 支持多轮交互，延迟降低2.5倍，适合复杂长周期任务场景。
序列式LLM代理在具有硬约束（如预算和多样性要求）的长程规划中表现不佳，随着上下文增长，容易偏离全局约束。本文提出HiMAP-Travel，一种分层多智能体框架，将规划分解为战略协调与日级并行执行。协调器跨天分配资源，日执行器独立并行规划。三个关键机制支撑：交易监控器跨并行智能体强制执行预算与唯一性约束；谈判协议允许智能体拒绝不可行子目标并触发重规划；统一策略通过角色条件化训练，由GRPO优化，赋能所有智能体。在TravelPlanner数据集上，使用Qwen3-8B模型，验证集与测试集最终通过率（FPR）分别达52.78%与52.65%。在相同模型、训练与工具条件下，相比序列式DeepTravel基线，性能提升8.67~10.0个百分点；优于ATLAS达+17.65个百分点。在FlexTravelBench多轮场景中，2轮与3轮任务的FPR分别为44.34%与37.42%，同时通过并行化使延迟降低2.5倍。
原文摘要 · Abstract (English)
Sequential LLM agents fail on long-horizon planning with hard constraints like budgets and diversity requirements. As planning progresses and context grows, these agents drift from global constraints. We propose HiMAP-Travel, a hierarchical multi-agent framework that splits planning into strategic coordination and parallel day-level execution. A Coordinator allocates resources across days, while Day Executors plan independently in parallel. Three key mechanisms enable this: a transactional monitor enforcing budget and uniqueness constraints across parallel agents, a bargaining protocol allowing agents to reject infeasible sub-goals and trigger re-planning, and a single policy trained with GRPO that powers all agents through role conditioning. On TravelPlanner, HiMAP-Travel with Qwen3-8B achieves 52.78% validation and 52.65% test Final Pass Rate (FPR). In a controlled comparison with identical model, training, and tools, it outperforms the sequential DeepTravel baseline by +8.67~pp. It also surpasses ATLAS by +17.65~pp and MTP by +10.0~pp. On FlexTravelBench multi-turn scenarios, it achieves 44.34% (2-turn) and 37.42% (3-turn) FPR while reducing latency 2.5x through parallelization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。