Research paper

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

Published by Association for Computational LinguisticsJul 2026PDF

Learn how feedback from support copilots can inform which customer service tasks an AI may handle autonomously.

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows cover

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Nikita Borovkov, Elisei Rykov, Olga Tsymboi, Sergei Filimonov, Nikita Surnachev, Dmitry Bitman, Anatolii Potapov. Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track). © 2026 Association for Computational Linguistics. CC BY 4.0. 10.18653/v1/2026.acl-industry.141. Original PDF, unmodified.

CC BY 4.0

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

Related research.

ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?

Retrieval Enhancements for RAG: Insights from a Deployed Customer Support Chatbot

TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale