用客服反馈训练大模型，自动处理企业客服流程。
Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows
- 基于用户操作记录和简单修正反馈，训练可选择性执行的智能体。
- 上线两周实现45%流程自动化，平均处理时间减少39%。
- 适合需要高效客服系统的企业，尤其关注降本增效场景。
我们部署了一个在企业业务流程管理（BPM）平台内自动化端到端客户支持工作流的系统。该方法可在生产环境中规模化应用，新流程在两周内即可实现选择性自动化，利用已大规模生成的结构化每案界面交互日志和低开销的协作助手反馈——操作员仅需接受建议或提供修正。通过分阶段部署流程，系统训练下一界面动作策略，并从协作助手反馈中学习评估器以校准拒绝决策阈值，在后台仅执行高置信度步骤，对不确定操作则回退至人工并从更新的界面状态恢复。该设计使一名操作员可同时监督多个会话，仅在系统不确定时被中断。系统基于模式驱动的BPM界面视图构建，包含监控与安全回退机制。实际运行中，系统实现了45%会话的自动化，平均处理时间降低39%，且未影响支持质量水平。
原文摘要 · Abstract (English)
We present a deployed system that automates end-to-end customer support workflows inside an enterprise Business Process Management (BPM) platform. The approach is scalable in production and reaches selective automation within two weeks for a new process, leveraging supervision already generated at scale: structured per-case UI interaction traces and low-overhead copilot feedback, where operators either accept a suggestion or provide a correction. A staged deployment pipeline trains a next UI action policy, learns a critic from copilot feedback to calibrate abstention, and executes only high-confidence steps in the background while deferring uncertain decisions to operators and resuming from the updated UI state. This setup lets one operator supervise multiple concurrent sessions and be interrupted only when the system is uncertain. The system operates on a schema-driven view of the BPM interface and includes monitoring and safe fallbacks for production. In production, it automated 45% of sessions and reduced average handling time by 39% without degrading support quality level.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。