NEMO-4-PAYPAL: Leveraging NVIDIA's Nemo Framework for empowering PayPal's Commerce Agent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Garg, Sudhanshu, Wang, Andrew, Kulkarni, Chaitanya, Sahami, Ali, Farahani, Farhad, Chuang, Sean Yun-Shiuan, Wan, Jian, Manoharan, Srinivasan, Kona, Uma, Sharma, Nitin, Pang, Linsey, Mehrotra, Prakhar, Clark, Jessica, Moyou, Mark
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915712414515200
author Garg, Sudhanshu
Wang, Andrew
Kulkarni, Chaitanya
Sahami, Ali
Farahani, Farhad
Chuang, Sean Yun-Shiuan
Wan, Jian
Manoharan, Srinivasan
Kona, Uma
Sharma, Nitin
Pang, Linsey
Mehrotra, Prakhar
Clark, Jessica
Moyou, Mark
author_facet Garg, Sudhanshu
Wang, Andrew
Kulkarni, Chaitanya
Sahami, Ali
Farahani, Farhad
Chuang, Sean Yun-Shiuan
Wan, Jian
Manoharan, Srinivasan
Kona, Uma
Sharma, Nitin
Pang, Linsey
Mehrotra, Prakhar
Clark, Jessica
Moyou, Mark
contents We present the development and optimization of PayPal's Commerce Agent, powered by NEMO-4-PAYPAL, a multi-agent system designed to revolutionize agentic commerce on the PayPal platform. Through our strategic partnership with NVIDIA, we leveraged the NeMo Framework for LLM model fine-tuning to enhance agent performance. Specifically, we optimized the Search and Discovery agent by replacing our base model with a fine-tuned Nemotron small language model (SLM). We conducted comprehensive experiments using the llama3.1-nemotron-nano-8B-v1 architecture, training LoRA-based models through systematic hyperparameter sweeps across learning rates, optimizers (Adam, AdamW), cosine annealing schedules, and LoRA ranks. Our contributions include: (1) the first application of NVIDIA's NeMo Framework to commerce-specific agent optimization, (2) LLM powered fine-tuning strategy for retrieval-focused commerce tasks, (3) demonstration of significant improvements in latency and cost while maintaining agent quality, and (4) a scalable framework for multi-agent system optimization in production e-commerce environments. Our results demonstrate that the fine-tuned Nemotron SLM effectively resolves the key performance issue in the retrieval component, which represents over 50\% of total agent response time, while maintaining or enhancing overall system performance.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21578
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NEMO-4-PAYPAL: Leveraging NVIDIA's Nemo Framework for empowering PayPal's Commerce Agent
Garg, Sudhanshu
Wang, Andrew
Kulkarni, Chaitanya
Sahami, Ali
Farahani, Farhad
Chuang, Sean Yun-Shiuan
Wan, Jian
Manoharan, Srinivasan
Kona, Uma
Sharma, Nitin
Pang, Linsey
Mehrotra, Prakhar
Clark, Jessica
Moyou, Mark
Artificial Intelligence
We present the development and optimization of PayPal's Commerce Agent, powered by NEMO-4-PAYPAL, a multi-agent system designed to revolutionize agentic commerce on the PayPal platform. Through our strategic partnership with NVIDIA, we leveraged the NeMo Framework for LLM model fine-tuning to enhance agent performance. Specifically, we optimized the Search and Discovery agent by replacing our base model with a fine-tuned Nemotron small language model (SLM). We conducted comprehensive experiments using the llama3.1-nemotron-nano-8B-v1 architecture, training LoRA-based models through systematic hyperparameter sweeps across learning rates, optimizers (Adam, AdamW), cosine annealing schedules, and LoRA ranks. Our contributions include: (1) the first application of NVIDIA's NeMo Framework to commerce-specific agent optimization, (2) LLM powered fine-tuning strategy for retrieval-focused commerce tasks, (3) demonstration of significant improvements in latency and cost while maintaining agent quality, and (4) a scalable framework for multi-agent system optimization in production e-commerce environments. Our results demonstrate that the fine-tuned Nemotron SLM effectively resolves the key performance issue in the retrieval component, which represents over 50\% of total agent response time, while maintaining or enhancing overall system performance.
title NEMO-4-PAYPAL: Leveraging NVIDIA's Nemo Framework for empowering PayPal's Commerce Agent
topic Artificial Intelligence
url https://arxiv.org/abs/2512.21578