MOOSE-Copilot: New AI System Enables Scientists to Interactively Guide Hypothesis Discovery
Researchers have introduced MOOSE-Copilot, a web-based AI assistant that unifies exploratory and fine-grained scientific hypothesis generation under human guidance. Unlike prior autonomous LLM-based approaches, it allows scientists to direct the process through structured feedback signals and an interactive visual interface. The system, accepted to ACL 2026, aims to make AI-assisted hypothesis discovery accessible to interdisciplinary researchers without requiring programming expertise.
MOOSE-Copilot is a unified framework designed to address two key shortcomings in current AI-driven scientific hypothesis discovery: the separation of broad exploratory search from detailed refinement, and the lack of meaningful human oversight. The system introduces a formalized human-AI interaction (HAII) protocol through which scientists provide three types of structured signals—initial blueprints, inter-stage routing decisions, and intra-stage feedback—to guide the generative process. Evaluations using an oracle-simulated setup, where an LLM mimics idealized expert input, demonstrated that structured human signals significantly outperform fully autonomous baselines. The accompanying web interface visualizes hypothesis search as an interactive tree, enabling researchers to select, route, and refine hypotheses without any command-line interaction. The paper has been accepted to the System Demonstrations track of ACL 2026, indicating peer recognition of its practical contribution to the field.
What's missing
The oracle-simulated evaluation relies on an LLM approximating expert signals rather than real human scientists, leaving open questions about performance with actual domain experts of varying backgrounds. Long-term usability studies and comparisons against other human-in-the-loop hypothesis generation tools are also absent.
What different sources said
- arXiv cs.AICenter
MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery
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.