Project Synapse: A Hierarchical Multi-Agent Framework with Hybrid Memory for Autonomous Resolution of Last-Mile Delivery Disruptions

TL;DR

Project Synapse presents a hierarchical multi-agent system with hybrid memory to autonomously resolve last-mile delivery disruptions, utilizing a new framework and benchmark dataset for validation.

Contribution

It introduces a novel hierarchical multi-agent framework with hybrid memory and workflow orchestration for autonomous disruption resolution in last-mile delivery.

Findings

Successfully managed 30 complex disruption scenarios

Validated system performance with LLM-based evaluation

Curated a benchmark dataset from real-world reviews

Abstract

This paper introduces Project Synapse, a novel agentic framework designed for the autonomous resolution of last-mile delivery disruptions. Synapse employs a hierarchical multi-agent architecture in which a central Resolution Supervisor agent performs strategic task decomposition and delegates subtasks to specialized worker agents responsible for tactical execution. The system is orchestrated using LangGraph to manage complex and cyclical workflows. To validate the framework, a benchmark dataset of 30 complex disruption scenarios was curated from a qualitative analysis of over 6,000 real-world user reviews. System performance is evaluated using an LLM-as-a-Judge protocol with explicit bias mitigation.