arXiv cs.CLPaper
Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents
Small models can be made competitive on structured interactive tasks through targeted diagnostics and RL. The wins here are real: clemscore goes from 10.67 to 38.92. The recipe is generalizable: acquire broad coverage, fix local failures, preserve general ability. If you're working with small models in constrained domains, this is a template that works.