EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce

2026-04-26

AI Summary

This work addresses the problem of heterogeneous product naming in e-commerce titles caused by promotional phrases, platform tags, and bundle descriptions. To tackle this challenge, the authors propose EPM-RL, a novel framework that introduces reinforcement learning to product matching for the first time. EPM-RL leverages parameter-efficient fine-tuning (PEFT) of large language models (LLMs) for generative reasoning, initialized with human-annotated data, and incorporates a multi-agent composite reward mechanism to distill high-latency, costly multi-agent inference into a private, end-to-end deployable local model. Compared to baselines relying solely on PEFT or commercial APIs, EPM-RL achieves higher matching accuracy while significantly reducing latency and deployment costs, making it suitable for privacy-sensitive, large-scale enterprise applications.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Prompt Engineering / Prompting
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Product mapping, the task of deciding whether two e-commerce listings refer to the same product, is a core problem for price monitoring and channel visibility. In real marketplaces, however, sellers frequently inject promotional keywords, platform-specific tags, and bundle descriptions into titles, causing the same product to appear under many different names. Recent LLM-based and multi-agent frameworks improve robustness and interpretability on such hard cases, but they often rely on expensive external APIs, repeated retrieval, and complex inference-time orchestration, making large-scale deployment costly and difficult in privacy-sensitive enterprise settings. To address these issues, we present EPM-RL, a reinforcement-learning-based framework for building an accurate and efficient on-premise e-commerce product mapping model. Our central idea is to distill high-cost agentic reasoning into a trainable in-house model. Starting from a curated set of product pairs with LLM-generated rationales and human verification, we first perform parameter-efficient fine-tuning (PEFT) on a small student model using structured reasoning outputs. We then further optimize the model with Reinforcement Learning (RL) using an agent-based reward that jointly evaluates output-format compliance, label correctness, reasoning--preference scores from specially designed judge models. Preliminary results show that EPM-RL consistently improves over PEFT-only training and offers a stronger quality--cost trade-off than commercial API-based baselines, while enabling private deployment and lower operational cost. These findings suggest that reinforcement learning can turn product mapping from a high-latency agentic pipeline into a scalable, inspectable, and production-ready in-house system.

Problem

• product mapping
• e-commerce
• on-premise deployment
• privacy-sensitive
• promotional noise

Innovation

• Reinforcement Learning
• On-Premise Deployment
• Product Mapping
• Parameter-Efficient Fine-Tuning
• LLM Distillation