Alibaba's G-CAST: governed continual self-training keeps e-commerce agents fresh in production

Yuechun Yu · hf · 2026-11-16

The G-CAST paper tackles two production problems for LLM e-commerce agents: demand drift (new categories and scenarios outdating a one-shot-trained model) and harness evolution (model must adopt new tools/skills without breaking behavior users rely on).

Core mechanisms:

Experiments on a real production agent show stronger adaptation to new demands and better retention of accepted behavior than a strong autonomous post-training baseline, with ablations confirming both components matter. G-CAST is deployed on Yuancai, Alibaba 1688's B2B procurement agent.

Original post →

More from coding & agent

coding & agent channel →