Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework

2026-02-17

AI Summary

Existing customer service automation approaches either rely on complex module orchestration or simplified instruction templates, resulting in poor generalization, high deployment costs, and significant privacy risks. This work proposes an end-to-end automation framework that eliminates the need for orchestration by introducing task-oriented flowcharts (TOFs) to guide small language models in executing service tasks. The framework supports local deployment and integrates decentralized knowledge distillation to address data scarcity and privacy concerns. We also design a low-cost algorithm for automatic flowchart construction and release an open-source, interactive web platform. Experimental results demonstrate that our method significantly outperforms mainstream baselines and commercial systems across multiple service tasks, achieving strong quantitative metrics and practical deployment efficacy.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Auto ML and Hyperparameter Tuning
• Natural Language Processing: (Large) Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Customer service automation has seen growing demand within digital transformation. Existing approaches either rely on modular system designs with extensive agent orchestration or employ over-simplified instruction schemas, providing limited guidance and poor generalizability. This paper introduces an orchestration-free framework using Task-Oriented Flowcharts (TOFs) to enable end-to-end automation without manual intervention. We first define the components and evaluation metrics for TOFs, then formalize a cost-efficient flowchart construction algorithm to abstract procedural knowledge from service dialogues. We emphasize local deployment of small language models and propose decentralized distillation with flowcharts to mitigate data scarcity and privacy issues in model training. Extensive experiments validate the effectiveness in various service tasks, with superior quantitative and application performance compared to strong baselines and market products. By releasing a web-based system demonstration with case studies, we aim to promote streamlined creation of future service automation.

Problem

• customer service automation
• agent orchestration
• privacy preservation
• generalizability
• data scarcity

Innovation

• orchestration-free
• Task-Oriented Flowcharts
• privacy-preserving
• decentralized distillation
• small language models