# ATLAS: Active Theory Learning for Automated Science

arXiv: https://arxiv.org/abs/2606.12386 · HTML: https://mlsanity.com/paper/2606.12386/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 63 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 13 of 13)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Modern Bayesian Experimental Design](https://mlsanity.com/paper/2302.14545/) (2023)
- [Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design](https://mlsanity.com/paper/2103.02438/) (2021)
- [Optimal experimental design: Formulations and computations](https://mlsanity.com/paper/2407.16212/) (2024)
- [Meta-trained agents implement Bayes-optimal agents](https://mlsanity.com/paper/2010.11223/) (2020)
- [Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities](https://mlsanity.com/paper/2208.00549/) (2022)
- [Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction](https://mlsanity.com/paper/2410.14240/) (2024)
- [Automating the Practice of Science -- Opportunities, Challenges, and Implications](https://mlsanity.com/paper/2409.05890/) (2024)
- [Generating Computational Cognitive Models using Large Language Models](https://mlsanity.com/paper/2502.00879/) (2025)
- [Practical optimal experiment design with probabilistic programs](https://mlsanity.com/paper/1608.05046/) (2016)
- [Toward an automated science of the mind](https://mlsanity.com/paper/2603.20988/) (2026)
- [Adversarial construction as a potential solution to the experiment design problem in large task spaces](https://mlsanity.com/paper/2602.03172/) (2026)

## Built on by (most cited first, 5 of 5)

- [Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist](https://mlsanity.com/paper/2606.26448/) (2026)
- [Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models](https://mlsanity.com/paper/2608.09696/) (2026)
- [auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation](https://mlsanity.com/paper/2606.26460/) (2026)
- [Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space](https://mlsanity.com/paper/2610.07627/) (2026)
- [Triage-PiEvo: Evidence Admission for Principle-Evolving Scientific Agents](https://mlsanity.com/paper/2610.14683/) (2026)

## Abstract (arXiv)

Advancing scientific understanding through mechanistic modeling requires posing the right experimental questions to yield maximally informative data. To automate this pursuit within cognitive science, we introduce ATLAS (Active Theory Learning for Automated Science), an active learning framework for the data-driven discovery of interpretable behavioral models. ATLAS iterates between generating mechanistic hypotheses--instantiated as a diverse ensemble of sparse neural networks (Disentangled RNNs)--and designing experiments that optimally distinguish between them. We test this approach on the problem of recovering reinforcement learning agents from their behavior in bandit tasks. ATLAS designs varied sequences of qualitatively novel experiments with temporal structure tailored to underlying agent characteristics. The models trained on these experiments are evaluated against a comprehensive set of metrics for mechanistic modeling that capture behavioral, structural, and computational similarity. ATLAS achieves a 5-10x improvement in sample efficiency across all metrics compared to random experimentation, and its performance is further validated against expert-designed experiments derived from literature. These in silico results showcase ATLAS's potential to accelerate human-interpretable insights in cognitive science and other domains where scientific inquiry relies on discovering mechanistic models.