Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2602.15377 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917277837819904 |
|---|---|
| author | Hong, Mengze Zhang, Chen Jason Guo, Zichang Gu, Hanlin Jiang, Di Qing, Li |
| author_facet | Hong, Mengze Zhang, Chen Jason Guo, Zichang Gu, Hanlin Jiang, Di Qing, Li |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15377 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework Hong, Mengze Zhang, Chen Jason Guo, Zichang Gu, Hanlin Jiang, Di Qing, Li Computation and Language Artificial Intelligence 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. |
| title | Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.15377 |