knowledge-acquisition

This paper introduces LittleLearner, a 5B-parameter language model trained on a curated elementary-grade corpus, to study knowledge acquisition in a controlled sandbox environment.

CLBench-V is a benchmark for evaluating multimodal context learning across grounding, new information application, and new knowledge learning. The best model achieves only 0.2847, showing the task remains challenging.

Introduces 'Machine Studying' as a problem where AI agents must autonomously develop expertise from a corpus, beyond RAG or long-context, and presents the StudyBench benchmark for evaluation.