Year: 2025
Type: preprint
Abstract: Enterprise AI agents must continuously adapt to maintain accuracy, reduce latency, and remain aligned with user needs. We present a practical implementation of a data flywheel in NVInfo AI, NVIDIA's Mixture-of-Experts (MoE) Knowledge Assistant serving over 30,000 employees. By operationalizing a MAPE-driven data flywheel, we built a closed-loop system that systematically addresses failures in retrieval-augmented generation (RAG) pipelines and enables continuous learning. Over a 3-month post-deployment period, we monitored feedback and collected 495 negative samples. Analysis revealed two major failure modes: routing errors (5.25\%) and query rephrasal errors (3.2\%). Using NVIDIA NeMo microservices, we implemented targeted improvements through fine-tuning. For routing, we replaced a Llama 3.1 70B model with a fine-tuned 8B variant, achieving 96\% accuracy, a 10x reduction in model size, and 70\% latency improvement. For query rephrasal, fine-tuning yielded a 3.7\% gain in accuracy and a 40\% latency reduction. Our approach demonstrates how human-in-the-loop (HITL) feedback, when structured within a data flywheel, transforms enterprise AI agents into self-improving systems. Key learnings include approaches to ensure agent robustness despite limited user feedback, navigating privacy constraints, and executing staged rollouts in production. This work offers a repeatable blueprint for building robust, adaptive enterprise AI agents capable of learning from real-world usage at scale.
Source: arXiv (Cornell University)
Authors: Shukla, Aaditya, Knowles, Sidney, Madugula, Meenakshi, Farris, Dave, Angilly, Ryan, Pombo, Santiago, Xu, Anbang, An, Lu, Balasubramanian, Abhinav, Yu, Tan, Ren, Jiaxiang, Akkiraju, Rama
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415914390
Cites:
Cited by:
Related to: