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

arXiv: https://arxiv.org/abs/2512.21578 · HTML: https://mlsanity.com/paper/2512.21578/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 25 Dec 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 7 of 7)

- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Query Expansion by Prompting Large Language Models](https://mlsanity.com/paper/2305.03653/) (2023)
- [Rethinking E-Commerce Search](https://mlsanity.com/paper/2312.03217/) (2023)
- [LESER: Learning to Expand via Search Engine-feedback Reinforcement in e-Commerce](https://mlsanity.com/paper/2509.05570/) (2025)

## Built on by (most cited first, 1 of 1)

- [Accelerating PayPal's Commerce Agent with Speculative Decoding: An Empirical Study on EAGLE3 with Fine-Tuned Nemotron Models](https://mlsanity.com/paper/2604.19767/) (2026)

## Abstract (arXiv)

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.