Skip to content
Live
Hugging Face Daily Papers·· yesterday65

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

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

Brief overview

G-CAST addresses the challenges of e-commerce agents under changing demands and capabilities by transforming daily production evidence into reward-guided, entropy-priority training data and governance reward evolution. The system controls model updates under cumulative evaluation, enabling the agent to learn new behaviors without sacrificing existing capabilities. Real e-commerce agent experiments show that G-CAST outperforms strong self-supervised post-training baselines in new demand adaptation and old behavior retention, and that reward routing, entropy-priority data orchestration, and governance reward evolution are all crucial for performance improvement.

Article

Published on Nov 13

Authors:

,

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.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2611.17814

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.17814 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.17814 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.17814 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

Source: Hugging Face Daily Papers · huggingface.co