ATLAS: New AI Framework Automates Scientific Discovery Through Active Learning
Researchers have introduced ATLAS (Active Theory Learning for Automated Science), an AI framework that autonomously generates mechanistic hypotheses and designs experiments to distinguish between them. The system was tested on recovering reinforcement learning agent models from behavioral data in bandit tasks, using sparse neural networks called Disentangled RNNs. ATLAS achieved a 5–10x improvement in sample efficiency over random experimentation, suggesting potential to accelerate scientific discovery in cognitive science and related fields.
ATLAS is an active learning framework developed to automate the data-driven discovery of interpretable behavioral models in cognitive science. The system operates in an iterative loop: it first generates a diverse ensemble of mechanistic hypotheses instantiated as sparse neural networks (Disentangled RNNs), then designs experiments optimally tailored to distinguish between competing hypotheses. The framework was evaluated on the task of inferring reinforcement learning agents from their behavior in bandit tasks, a standard paradigm in cognitive and behavioral research. Performance was assessed using a comprehensive suite of metrics capturing behavioral, structural, and computational similarity between recovered and true models. ATLAS demonstrated a 5–10x gain in sample efficiency relative to random experimentation and was also benchmarked against expert-designed experiments from the scientific literature. All experiments were conducted in silico, meaning results reflect simulated rather than real-world cognitive science data. The authors argue the approach could generalize beyond cognitive science to any domain where scientific inquiry depends on discovering mechanistic models.
What's missing
All experiments were conducted in silico using simulated agents; it remains unknown how ATLAS performs when applied to real human or animal behavioral data.
What different sources said
- arXiv cs.AICenter
ATLAS: Active Theory Learning for Automated Science
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.