Reproduce “CRMAgent: A Multi-Agent LLM System for E-Commerce CRM Message Template Generation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yinzhu Quan, Xinrui Li, Ying Chen
CRMAgent rewrites promotional messages for customer segments using successful campaign examples. It draws on messages from the same merchant and audience group, then retrieves campaigns across merchants, and falls back to rule-based rewriting when references are unavailable. In 3,957 cases, GPT-4o ratings improved and generated text was preferred 78.44% of the time; these are evaluator judgments, not measured customer outcomes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.