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

• URL: http://arxiv.org/abs/2602.15377v1
• Date: Tue, 17 Feb 2026 06:17:37 GMT
• 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,
• Abstract summary: This paper introduces an orchestration-free framework using Task-Oriented Flowcharts (TOFs)<n>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.<n>By releasing a web-based system demonstration with case studies, we aim to promote streamlined creation of future service automation.
• Score: 16.034888856877565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation [54.945281159783896]
  We present a scalable pipeline for automatically generating high-quality training data for web agents.<n>We introduce a novel constraint-based evaluation framework that provides fine-grained assessment of progress towards task completion.
  arXiv  Detail & Related papers  (2026-02-13T02:52:18Z)
• WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents [12.014029662322152]
  Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks.<n>We propose WISE-Flow, a feasibility-centric framework that converts historical service interactions into reusable procedural experience.
  arXiv  Detail & Related papers  (2026-01-13T02:43:41Z)
• FLAS: a combination of proactive and reactive auto-scaling architecture for distributed services [0.0]
  We present FLAS (Forecasted Load Auto-Scaling), an auto-scaler for distributed services.<n>It combines the advantages of proactive and reactive approaches according to the situation to decide the optimal scaling actions.<n>We provide a FLAS implementation for the use case of a content-based publish-subscribe distributed systems.
  arXiv  Detail & Related papers  (2025-10-23T09:38:07Z)
• AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents [15.41283323575065]
  AutoEDA is a framework for EDA automation that leverages paralleled learning through the Model Context Protocol (MCP) specific for standardized and scalable natural language experience.<n>Results from experiments show improvements in automation accuracy and efficiency, as well as script quality when compared to existing methods.
  arXiv  Detail & Related papers  (2025-08-01T18:23:57Z)
• SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling [58.05959902776133]
  We introduce Single-Pass.<n>with Reference-Guided Evaluation (SPARE), a novel structured framework that enables efficient per-step annotation.<n>We demonstrate SPARE's effectiveness across four diverse datasets spanning mathematical reasoning (GSM8K, MATH), multi-hop question answering (MuSiQue-Ans), and spatial reasoning (SpaRP)<n>On ProcessBench, SPARE demonstrates data-efficient out-of-distribution generalization, using only $sim$16% of training samples compared to human-labeled and other synthetically trained baselines.
  arXiv  Detail & Related papers  (2025-06-18T14:37:59Z)
• MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision [76.42361936804313]
  We introduce MAS-ZERO, the first self-evolved, inference-time framework for automatic MAS design.<n> MAS-ZERO employs meta-level design to iteratively generate, evaluate, and refine MAS configurations tailored to each problem instance.
  arXiv  Detail & Related papers  (2025-05-21T00:56:09Z)
• Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning [8.95038939248447]
  Continual instruction tuning enables large language models to learn incrementally while retaining past knowledge.<n>Our framework dynamically filters incoming data, which identify and reduce redundant data across successive updates.<n>It reduces computational costs by 66.7% and improved model performance, and achieved autonomous updates.
  arXiv  Detail & Related papers  (2025-03-20T08:00:41Z)
• Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents [65.36060818857109]
  We present a novel framework for extracting and evaluating dialog from historical interactions.<n>Our extraction process consists of two key stages: (1) a retrieval step to select relevant conversations based on key procedural elements, and (2) a structured workflow generation process using a question-answer-based chain-of-thought (QA-CoT) prompting.
  arXiv  Detail & Related papers  (2025-02-24T16:55:15Z)
• CELA: Cost-Efficient Language Model Alignment for CTR Prediction [70.65910069412944]
  Click-Through Rate (CTR) prediction holds a paramount position in recommender systems.<n>Recent efforts have sought to mitigate these challenges by integrating Pre-trained Language Models (PLMs)<n>We propose textbfCost-textbfEfficient textbfLanguage Model textbfAlignment (textbfCELA) for CTR prediction.
  arXiv  Detail & Related papers  (2024-05-17T07:43:25Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Inverse Reinforcement Learning of Autonomous Behaviors Encoded as Weighted Finite Automata [18.972270182221262]
  This paper presents a method for learning logical task specifications and cost functions from demonstrations. We employ a spectral learning approach to extract a weighted finite automaton (WFA), approximating the unknown logic structure of the task. We define a product between the WFA for high-level task guidance and a Labeled Markov decision process (L-MDP) for low-level control and optimize a cost function that matches the demonstrator's behavior.
  arXiv  Detail & Related papers  (2021-03-10T06:42:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.