G-CAST: Governed Continual Self-Training for E-Commerce Agents under Evolving Demands Alibaba researchers deployed G-CAST, a governed continual self-training system, on Yuancai (cai.1688.com), the B2B procurement agent on Alibaba's 1688 platform, according to an arXiv paper (2611.17814v1). G-CAST converts daily production evidence under evolving demand and capability contracts into reward-routed, entropy-prioritized training data and governed reward evolution, with governed checkpoint transitions under cumulative evaluation controlling each model update. Experiments on a real production e-commerce agent showed G-CAST adapted more strongly to newly introduced demand while better preserving previously accepted behavior than a strong autonomous post-training baseline, and ablations found both the data orchestration and governed reward evolution important to those gains. arXiv:2611.17814v1 Announce Type: cross 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 http://cai.1688.com/ , a B2B procurement agent on Alibaba's 1688 platform.