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

TL;DR

This paper demonstrates how leveraging NVIDIA's NeMo framework for fine-tuning large language models significantly improves the performance and efficiency of PayPal's multi-agent commerce system, especially in retrieval tasks.

Contribution

It introduces the first application of NVIDIA's NeMo framework for optimizing commerce-specific agents and presents a scalable fine-tuning strategy for multi-agent systems in e-commerce.

Findings

Significant reduction in latency and cost for the retrieval component.

Effective fine-tuning of Nemotron SLM improves overall agent response time.

Maintains or enhances system performance while optimizing key bottlenecks.

Abstract

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.