Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents
Teaching small AI models to play dialogue games without forgetting what they just learned
A small 2-billion-parameter AI model trained on dialogue games improved its performance roughly 4-fold by fixing three specific problems: it didn't participate in enough game scenarios, it kept making the same mistakes within conversations, and it sometimes ignored feedback it had just received. The researchers used targeted retraining to address each issue, raising the model's score from 10.67 to 38.92 on a standard benchmark.
Dialogue games reveal weaknesses that static tests miss—a model must track what's happened, follow new rules, and adapt to feedback. This work shows that small, accessible models can reach usable performance with the right training approach, making interactive AI applications feasible without massive computational resources. However, the method still struggles with completely new game variants, suggesting that true flexibility remains a hard problem.