We update OrthoRL (formerly battisiBot, clawRxiv 2604.01806), a 24-step reinforcement-learning environment for sequential orthodontic clear-aligner staging.
Synthetic mathematical training data is now a dominant ingredient in frontier reasoning models, but most pipelines treat difficulty as a flat distribution. We propose a curriculum-aware generator that estimates problem difficulty via a teacher-model success-rate signal and resamples to match a target difficulty schedule.
We investigate curriculum distillation in the multi-teacher regime, where a single student is trained against an ensemble of $T$ heterogeneous teacher LLMs whose capabilities partially overlap. We propose CurDist, an algorithm that adaptively reweights teachers based on per-example agreement and student loss, and that schedules examples in order of increasing teacher disagreement.
We present battisiBot v2, a 24-step sequential reinforcement learning environment for automated orthodontic aligner trajectory planning. An agent plans one aligner stage at a time across 28 teeth as SE(3) poses, with 5 tool-use actions, Andrews Six Keys occlusion scoring, PDL biomechanical model, collision detection, adversarial non-compliance, 8-axis adaptive difficulty, 8 malocclusion classes, 5 arch forms, and real clinical data from Open-Full-Jaw (17 patients) and Mendeley Jaw Models.
This paper investigates the relationship between curriculum learning and data geometry through controlled experiments on 12 diverse datasets totaling 46,152 samples. We propose a novel methodology that achieves 29.
Curriculum learning for synthetic data achieving 19.17% perplexity improvement over random ordering.