# CRMAgent: A Multi-Agent LLM System for E-Commerce CRM Message Template Generation

arXiv: https://arxiv.org/abs/2507.08325 · HTML: https://mlsanity.com/paper/2507.08325/

## Key facts

- Cited by 6 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 12 of its 30 references that are in the map.
- First posted on arXiv 11 Jul 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, 12 of 12)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [A Retrieve-and-Edit Framework for Predicting Structured Outputs](https://mlsanity.com/paper/1812.01194/) (2018)
- [Large Language Model Supply Chain: A Research Agenda](https://mlsanity.com/paper/2404.12736/) (2024)
- [EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning](https://mlsanity.com/paper/2405.07938/) (2024)
- [DocAgent: A Multi-Agent System for Automated Code Documentation Generation](https://mlsanity.com/paper/2504.08725/) (2025)
- [EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments](https://mlsanity.com/paper/2506.08136/) (2025)
- [EconNLI: Evaluating Large Language Models on Economics Reasoning](https://mlsanity.com/paper/2407.01212/) (2024)
- [MAxPrototyper: A Multi-Agent Generation System for Interactive User Interface Prototyping](https://mlsanity.com/paper/2405.07131/) (2024)
- [Retrieval of Temporal Event Sequences from Textual Descriptions](https://mlsanity.com/paper/2410.14043/) (2024)
- [Leveraging Large Language Models for Risk Assessment in Hyperconnected Logistic Hub Network Deployment](https://mlsanity.com/paper/2503.21115/) (2025)

## Built on by (most cited first, 6 of 6)

- [AutoBnB-RAG: Enhancing Multi-Agent Incident Response with Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.13118/) (2025)
- [Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation](https://mlsanity.com/paper/2604.16958/) (2026)
- [EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data](https://mlsanity.com/paper/2609.19523/) (2026)
- [AgentBnB: A Browser-Based Cybersecurity Tabletop Exercise with Large Language Model Support and Retrieval-Aligned Scaffolding](https://mlsanity.com/paper/2511.00265/) (2025)
- [I Am AdMan: A Pipeline for Automatic Generation of Personalized Advertising Imagery](https://mlsanity.com/paper/2609.12694/) (2026)
- [AutoMARS: Automatic and Scalable Multi-Agent Large Language Model Framework for Supply Chain Risk Assessment](https://mlsanity.com/paper/2610.17206/) (2026)

## Abstract (arXiv)

In e-commerce private-domain channels such as instant messaging and e-mail, merchants engage customers directly as part of their Customer Relationship Management (CRM) programmes to drive retention and conversion. While a few top performers excel at crafting outbound messages, most merchants struggle to write persuasive copy because they lack both expertise and scalable tools. We introduce CRMAgent, a multi-agent system built on large language models (LLMs) that generates high-quality message templates and actionable writing guidance through three complementary modes. First, group-based learning enables the agent to learn from a merchant's own top-performing messages within the same audience segment and rewrite low-performing ones. Second, retrieval-and-adaptation fetches templates that share the same audience segment and exhibit high similarity in voucher type and product category, learns their successful patterns, and adapts them to the current campaign. Third, a rule-based fallback provides a lightweight zero-shot rewrite when no suitable references are available. Extensive experiments show that CRMAgent consistently outperforms merchants' original templates, delivering significant gains in both audience-match and marketing-effectiveness metrics.