What Makes a Sale? Rethinking End-to-End Seller--Buyer Retail Dynamics with LLM Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910105648234496 |
|---|---|
| author | Choi, Jeonghwan Hwang, Jibin Sun, Gyeonghun Ban, Minjeong Yun, Taewon Cheon, Hyeonjae Song, Hwanjun |
| author_facet | Choi, Jeonghwan Hwang, Jibin Sun, Gyeonghun Ban, Minjeong Yun, Taewon Cheon, Hyeonjae Song, Hwanjun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04468 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | What Makes a Sale? Rethinking End-to-End Seller--Buyer Retail Dynamics with LLM Agents Choi, Jeonghwan Hwang, Jibin Sun, Gyeonghun Ban, Minjeong Yun, Taewon Cheon, Hyeonjae Song, Hwanjun Artificial Intelligence Computation and Language 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. |
| title | What Makes a Sale? Rethinking End-to-End Seller--Buyer Retail Dynamics with LLM Agents |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2604.04468 |