[2602.15377] Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework
Summary
This paper presents an orchestration-free framework for customer service automation, utilizing Task-Oriented Flowcharts (TOFs) to enhance efficiency and privacy in service tasks without manual intervention.
Why It Matters
As businesses increasingly adopt automation for customer service, this framework addresses critical issues such as data privacy and the limitations of existing modular systems. By providing a cost-effective and efficient solution, it aims to improve the scalability and effectiveness of automated customer interactions.
Key Takeaways
- Introduces a framework for end-to-end customer service automation without orchestration.
- Utilizes Task-Oriented Flowcharts to abstract procedural knowledge from dialogues.
- Emphasizes local deployment of small language models to enhance privacy.
- Demonstrates superior performance in various service tasks compared to existing solutions.
- Includes a web-based system demonstration to facilitate future automation development.
Computer Science > Computation and Language arXiv:2602.15377 (cs) [Submitted on 17 Feb 2026] Title:Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework Authors:Mengze Hong, Chen Jason Zhang, Zichang Guo, Hanlin Gu, Di Jiang, Li Qing View a PDF of the paper titled Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework, by Mengze Hong and 5 other authors View PDF HTML (experimental) 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 demonstrat...