When Agent Becomes the Scientist – Building Closed-Loop System from Hypothesis to Verification

Systematically learn and evaluate manifolds from high-dimensional data

This is the official repository for HypoGeniC (Hypothesis Generation in Context) and HypoRefine, which are automated, data-driven tools that leverage large language models to generate hypothesis for open-domain research. For more details, please see the original paper using the link below.

Official implementation of the ACL 2024: Scientific Inspiration Machines Optimized for Novelty

AGATHA: Automatic Graph-mining And Transformer based Hypothesis generation Approach

Locally hosted AI Agent Python Tool To Generate Novel Research Hypothesis + Titles + Abstracts

A platform for Interactive AI-assisted Hypothesis Generation [ACL 2025]

Deep Critical Research Agent : The first AI-driven Critical Analysis to turn the huge amount of preclinical biology data and information into knowledge and hence disease cures.

Symbolic XAI explainable machine learning & non-linear regression platform for MATLAB

AstroAgents: Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data

Workflow to generate interactive feature selection report for cross-sectional or longitudinal studies

A open source Literature Based Discovery system, using Groovy & Grails, including a re-implementation of the Arrowsmith algorithm(s)

A Python library for creating and exploring structured review articles.

How do you train retrievers to find inspirations? [ACL 2025]

Case Studies & Problems based on Data Science Lifecycle Framework - Problem Formulation, Hypothesis Building, Data Extraction and Cleaning, Data Modeling and Post Modeling

AI reasoning engine creating new, never-before-seen hypotheses across disciplines.Cross-domain AI reasoning framework for automatic hypothesis generation, symbolic formula inference, and scientific visualization.

Predict Loan Eligibility for a Finance company

Analysis of the operator's efficiency in a virtual communication company.

By integrating geographical data analysis and statistical modeling, CTCA aims to inform strategies for reducing crash rates and enhancing road safety. This initiative combines innovative data processing techniques with advanced analytics to offer actionable recommendations for policymakers, urban planners, and public safety organizations.