ATLAS uses active learning with disentangled RNN ensembles to design experiments that recover RL agent models from bandit behavior 5-10x more efficiently than random or expert baselines in simulations.
Bartlett, Suyog H
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLMs given only research questions from 1000 arXiv CS papers recommend a narrower set of methods than the original papers, with effective model-entity diversity dropping from 1232 to 59-96 and stronger agreement among LLMs than with papers.
citing papers explorer
-
ATLAS: Active Theory Learning for Automated Science
ATLAS uses active learning with disentangled RNN ensembles to design experiments that recover RL agent models from bandit behavior 5-10x more efficiently than random or expert baselines in simulations.
-
Thinking Like a Scientist? A Structural Study of LLM-Generated Research Methods
LLMs given only research questions from 1000 arXiv CS papers recommend a narrower set of methods than the original papers, with effective model-entity diversity dropping from 1232 to 59-96 and stronger agreement among LLMs than with papers.