shopping-agent-rl

provenance:github:junyi-lai/shopping-agent-rl

MiniCPM5-2B shopping agent, end-to-end: collection → filtering → curriculum SFT → GRPO/RLOO (veRL) → deterministic Final-200 eval. Strict success 3.0% → 76.5%.

View Source ↗First seen 1d agoNot yet hireable

PUBLIC HISTORY

First discoveredSep 24, 2026

IDENTITY

inferred

Identity inferred from code signals. No PROVENANCE.yml found.

Is this yours? Claim it →

METADATA

platformgithub

first seenSep 22, 2026

last updatedSep 23, 2026

last crawledtoday

version—

README BADGE

Add to your README:

![Provenance](https://getprovenance.dev/api/badge?id=provenance:github:junyi-lai/shopping-agent-rl)