AI RESEARCH
Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows
arXiv CS.CL
•
ArXi:2604.23855v1 Announce Type: new We present a deployed system that automates end-to-end customer 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.