Cover Image

Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Cen Mia, Zhang, Tiantian, Su, Hanchen, Zhang, Yufeng Wayne, Su, Shaowei, Xu, Mingzhi, Liu, Yu Elaine, Han, Wei, Werner, Jeremy, Cheng, Claire Na, Mehdad, Yashar
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM-Friendly Knowledge Representation for Customer Support
by: Su, Hanchen, et al.
Published: (2025)

Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback
by: Wu, Yisha, et al.
Published: (2025)

Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent Improvement
by: Shukla, Aaditya, et al.
Published: (2025)

CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production
by: Nie, Yixin, et al.
Published: (2026)

Extended Maternity Leave and Female Labour Supply: Evidence From a Regional Policy in China
by: Mingzhi Hu, et al.
Published: (2025)

Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement
by: Su, Hong
Published: (2025)

Pricing, Mergers, and Regulation Under the AI Flywheel Effect
by: Yuzhou Chen, et al.
Published: (2025)

Beyond IVR: Benchmarking Customer Support LLM Agents for Business-Adherence
by: Balaji, Sumanth, et al.
Published: (2026)

Multi-Dimensional Evaluation of Sustainable City Trips with LLM-as-a-Judge and Human-in-the-Loop
by: Banerjee, Ashmi, et al.
Published: (2026)

Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency
by: Jeon, Sungho, et al.
Published: (2023)

HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation
by: Gu, Yi, et al.
Published: (2026)

LoopBench: Discovering Emergent Symmetry Breaking Strategies with LLM Swarms
by: Parsaee, Ali, et al.
Published: (2025)

Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement
by: Liu, Fengrui, et al.
Published: (2026)

An LLM-Driven Closed-Loop Autonomous Learning Framework for Robots Facing Uncovered Tasks in Open Environments
by: Su, Hong
Published: (2026)

MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents
by: Gong, Ming, et al.
Published: (2025)

Characteristics Study and Floating Magnet Structure Improvement of Airflow Energy Harvester Based on Diamagnetic Levitation
by: Zhiyong Pang, et al.
Published: (2026)

Detecting gravitational wave background with equivalent configurations in the network of space based optical lattice clocks
by: Lou, Mingzhi, et al.
Published: (2026)

Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning
by: Su, Guangxin, et al.
Published: (2024)

Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding
by: Wang, Xiao, et al.
Published: (2024)

ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support
by: Chen, Tiantian, et al.
Published: (2026)

Time Matters: Under/Overperformance Duration and Performance Improvements in the Public Sector
by: Shaowei Chen, et al.
Published: (2026)

Exploring the Use of Autonomous Unmanned Vehicles for Supporting Power Grid Operations
by: Zhou, Yuqi, et al.
Published: (2024)

Paper 100: The Self-Sustaining Coupling Loop — Thermal Flywheel Governance, Passive Emission Readout, and the Closed Coupling Sequence
by: Dunn, James E.
Published: (2026)

RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis
by: Shen, Shaowei, et al.
Published: (2026)

Espiritismo:The Flywheel of the Puerto Rican Spiritual Traditions
by: Edil Torres Rivera
Published: (2005)

Compact UWB Slot Antenna With Dual‐Circular Polarization and Improvement of CP Performance
by: Leili Soleimani, et al.
Published: (2024)

Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents
by: Wang, Yufeng
Published: (2026)

FlyRoute: Self-Evolving Agent Profiling via Data Flywheel for Adaptive Task Routing
by: Li, Rongjun, et al.
Published: (2026)

Land financialisation and housing prices: evidence from China
by: Yinxin Su, et al.
Published: (2024)

Institutional Fragility and Entrepreneurial Activities
by: Mingzhi Hu, et al.
Published: (2025)

LLM Agents Should Employ Security Principles
by: Zhang, Kaiyuan, et al.
Published: (2025)

LoopTrap: Termination Poisoning Attacks on LLM Agents
by: Xu, Huiyu, et al.
Published: (2026)

ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?
by: Wang, Haoxin, et al.
Published: (2025)

Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptation
by: Grannen, Jennifer, et al.
Published: (2025)

EduPlanner: LLM-Based Multi-Agent Systems for Customized and Intelligent Instructional Design
by: Zhang, Xueqiao, et al.
Published: (2025)

Pioneer Agent: Continual Improvement of Small Language Models in Production
by: Atreja, Dhruv, et al.
Published: (2026)

Evil Geniuses: Delving into the Safety of LLM-based Agents
by: Tian, Yu, et al.
Published: (2023)

Improving Faithfulness of Abstractive Summarization by Controlling Confounding Effect of Irrelevant Sentences
by: Ghoshal, Asish, et al.
Published: (2022)

Communication-Aware Knowledge Distillation for Federated LLM Fine-Tuning over Wireless Networks
by: Zhang, Xinlu, et al.
Published: (2025)

Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications
by: Su, Guangxin, et al.
Published: (2025)