AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Efficient Adaptive Testing via Gradient Path Matching Subset Selection for AI Education

Yan Zhuang, Junhao Yu, Bohou Zhang, Zachary Pardos, Jinze Wu, Daoqiang Zhang

ICML 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
GPM gradient path matching instead of UATS meta-learningIRT adaptive testing · EXAM (step 20)AUC (%): 75.20 -> 77.89Improved
GPM instead of BECAT global gradient approximationIRT adaptive testing · ASSIST (step 20)AUC (%): 73.61 -> 75.27Improved
GPM instead of NCAT reinforcement learningIRT adaptive testing · NIPS-EDU (step 20)AUC (%): 76.66 -> 78.10Improved
GPM instead of FSI heuristicIRT adaptive testing · Ability estimation simulationtest length needed: up to 20% fewer questions; 9% on averageImproved
reduce training data to 50% for GPM (ablation)GPM · EXAMAUC (%): 77.89 -> 74.21Hurt
reduce training data to 50% for BOBCAT (ablation)BOBCAT · EXAMAUC (%): 72.88 -> 70.65Hurt
add 15% label noise to training for GPM (ablation)GPM · EXAMAUC (%): 77.89 -> 73.30Hurt
add 15% label noise to training for UATS (ablation)UATS · EXAMAUC (%): 73.45 -> 71.43Hurt
GPM under 15% noise vs best baseline GMOCATGPM · EXAM 15% noiseAUC (%): 72.50 -> 73.30Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy