Project Synapse：面向自主解决最后一公里配送中断的层次化多智能体框架与混合记忆
人工智能
2026-01-14 v1
摘要
本文介绍 Project Synapse，一种用于自主解决最后一公里配送中断的新型智能体框架。Synapse 采用层次化多智能体架构，由中心化的“问题解决主管”智能体负责战略任务分解，并将子任务分配给负责战术执行的专职工作智能体。该系统采用 LangGraph 进行编排，以管理复杂且可循环的工作流程。为验证该框架，本文从对超过 6000 条真实用户评论的定性分析中精选出 30 个复杂中断情景，构建了基准数据集。系统性能通过 LLM-as-a-Judge 协议进行评估，并包含明确的偏见缓解措施。
引用
@article{arxiv.2601.08156,
title = {Project Synapse: A Hierarchical Multi-Agent Framework with Hybrid Memory for Autonomous Resolution of Last-Mile Delivery Disruptions},
author = {Arin Gopalan Yadav and Varad Dherange and Kumar Shivam},
journal= {arXiv preprint arXiv:2601.08156},
year = {2026}
}
备注
We propose and evaluate a hierarchical LLM-driven multi-agent framework for adaptive disruption management in last-mile logistics, integrating planning, coordination, and natural-language reasoning. The system is validated through simulation-based experiments and qualitative analysis. Includes figures and tables. 33 pages