Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning
Shop-R1: 通过强化学习奖励大语言模型模拟在线购物中的人类行为
机构 * Michigan State University(密歇根州立大学) ; Amazon(亚马逊) ; Northeastern University(东北大学) ; University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) ; Northwestern University(西北大学)
AI总结 Shop-R1通过强化学习框架提升大语言模型在在线购物场景中模拟人类行为的推理能力,实现65%以上的性能提升。
Comments Accepted by ICLR 2026. The project page is available at https://damon-demon.github.io/shop-r1.html