← 研踪 PaperTrailarXiv:2611.03008 · v1
E-GenRM: Generative Reward Modeling for Open-Ended E-Commerce Shopping Agents
首次提交 2026-11-02 20:10
版本更新 2026-11-02 20:10
雷达观测 2026-11-04 23:42
摘要
We present E-GenRM (E-commerce Generative Reward Model), a generative reward model tailored to e-commerce shopping agents. User expectations are shifting from simple product queries to open-ended shopping tasks. However, existing trajectories and reward designs remain largely bounded by current agent usage patterns and known failures, providing limited guidance for further capability improvement. These limitations call for an integrated reward modeling framework for open-ended shopping agent tasks. On the data side, E-GenRM leverages naturally occurring user behavior across the shopping app to construct diverse, long-horizon conversational trajectories beyond established usage patterns. On the modeling side, E-GenRM first learns from behavior-grounded evaluation chains through supervised fine-tuning. It is then optimized through criterion-guided reinforcement learning, which rewards correct preference judgments and evidence-supported factual claims under each criterion. Personalized hard-negative training further improves its sensitivity to user preferences reflected in shopping behavior, beyond explicit requirements. We additionally develop an active evidence retrieval extension that acquires missing e-commerce information for evaluation. On E-GenRM-Bench, E-GenRM-27B achieves 87.40\% preference accuracy, outperforming the strongest baseline by 6.97 percentage points. In a 14-day online A/B test on Taobao, a shopping agent post-trained with E-GenRM improves the effective shopping-assistance rate by 1.39 percentage points and user satisfaction by 2.33 percentage points.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-02 20:10 · 最新观测版本
E-GenRM: Generative Reward Modeling for Open-Ended E-Commerce Shopping Agents
We present E-GenRM (E-commerce Generative Reward Model), a generative reward model tailored to e-commerce shopping agents. User expectations are shifting from simple product queries to open-ended shopping tasks. However, existing trajectories and reward designs remain largely bounded by current agent usage patterns and known failures, providing limited guidance for further capability improvement. These limitations call for an integrated reward modeling framework for open-ended shopping agent tasks. On the data side, E-GenRM leverages naturally occurring user behavior across the shopping app to construct diverse, long-horizon conversational trajectories beyond established usage patterns. On the modeling side, E-GenRM first learns from behavior-grounded evaluation chains through supervised fine-tuning. It is then optimized through criterion-guided reinforcement learning, which rewards correct preference judgments and evidence-supported factual claims under each criterion. Personalized hard-negative training further improves its sensitivity to user preferences reflected in shopping behavior, beyond explicit requirements. We additionally develop an active evidence retrieval extension that acquires missing e-commerce information for evaluation. On E-GenRM-Bench, E-GenRM-27B achieves 87.40\% preference accuracy, outperforming the strongest baseline by 6.97 percentage points. In a 14-day online A/B test on Taobao, a shopping agent post-trained with E-GenRM improves the effective shopping-assistance rate by 1.39 percentage points and user satisfaction by 2.33 percentage points.
查看此版本解读 →查看此版本原文 ↗