What Makes a Sale? Simulating End-to-End Seller-Buyer Retail Dynamics with LLM Agents
Jeonghwan Choi · Jibin Hwang · Gyeonghun Sun · Minjeong Ban · Taewon Yun · Hyeonjae Cheon · Hwanjun Song
RetailSim is a multi-agent LLM framework that unifies seller sales pitch, buyer interactions, and post-purchase outcomes in one pipeline, enabling causal analysis of how seller strategies propagate across stages to downstream conversion and revenue.
摘要
Evaluating retail strategies before deployment is difficult, as outcomes are determined across multiple stages, from seller-side persuasion through buyer–seller interaction to purchase decisions. However, existing retail simulators capture only partial aspects of this process and do not model cross-stage dependencies, making it difficult to assess how early decisions affect downstream outcomes. We present RetailSim, an end-to-end retail simulation framework that models this pipeline in a unified environment, explicitly designed for simulation fidelity through diverse product spaces, persona-driven agents, and multi-turn interactions. We evaluate RetailSim with a dual protocol comprising human evaluation of behavioral fidelity and meta-evaluation against real-world economic regularities, showing that it successfully reproduces key patterns such as demographic purchasing behavior, the price–demand relationship, and heterogeneous price elasticity. We further demonstrate its practical utility via decision-oriented use cases, including persona inference, seller–buyer interaction analysis, and sales strategy evaluation, showing RetailSim's potential as a controlled testbed for exploring retail strategies.