跳到正文
arXiv cs.AI· Yuechun Yu, Wenzheng Kong, Xiaofeng Mao, Jin Zhang·· 4 小时前AI 评分38

G-CAST:面向电商智能体持续需求演化的受治理持续自训练框架

G-CAST: Governed Continual Self-Training for E-Commerce Agents under Evolving Demands

AI 导读

阿里巴巴 1688 平台的 B2B 采购智能体 Yuancai 采用 G-CAST 持续自训练系统,应对用户需求漂移与执行工具演进两大挑战。该系统将日常生产数据转化为按奖励路由、按熵值优先排序的训练数据,并通过累积评测约束的受治理 checkpoint 切换来控制每次模型更新。

正文 · 原文

View PDF HTML (experimental)

Abstract:With the rapid advancement of Large Language Models (LLMs), an increasing number of users are turning to LLM-powered agents for conversational shopping in e-commerce. However, the user needs continue to change as new product categories, procurement scenarios, and feature requests emerge. At the same time, the product's execution harness-including its tools, skills, and operating procedures-continues to evolve to support increasingly sophisticated interactions. These changes create two practical challenges: 1) Demand drift alters the distribution, intent, and complexity of user requests, causing a model trained once to fall behind; 2) Harness evolution requires the model to use newly introduced capabilities correctly without losing behavior that users already rely on. Periodic manual retraining is too delayed and labor-intensive for this setting. To address these challenges, we present G-CAST, a governed continual self-training system that converts daily production evidence under evolving demand and capability contracts into reward-routed, entropy-prioritized training data and governed reward evolution. Governed checkpoint transition under cumulative evaluation controls each model update, enabling the agent to learn newly introduced behaviors without sacrificing previously accepted capabilities. Experiments on a real production e-commerce agent show that G-CAST achieves stronger adaptation to newly introduced demand while better preserving previously accepted behavior compared with a strong autonomous post-training baseline. Ablations further show that both reward-routed, entropy-prioritized data orchestration and governed reward evolution are important to these gains. G-CAST is now deployed in Yuancai(this http URL), a B2B procurement agent on Alibaba's 1688 platform.
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2611.17814 [cs.AI]
  (or arXiv:2611.17814v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.17814

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xiaofeng Mao [view email]
[v1] Fri, 13 Nov 2026 06:53:56 UTC (614 KB)

来源:arXiv cs.AI · arxiv.org