IIT Delhi Researchers Develop AI Tool To Conduct Scientific Experiment Independently
Indian Institute of Technology (IIT) Delhi researchers have developed an AI agent capable of independently conducting real-world scientific experiments, marking a shift from AI-assisted research to AI-driven laboratory work.
The AI system, named AILA (Artificially Intelligent Lab Assistant), can autonomously operate an Atomic Force Microscope (AFM), one of the most complex and sensitive instruments used in materials science, making real-time decisions, running experiments, and analysing results without human intervention. The findings have been published in the journal Nature Communications.
Developed by IIT Delhi researchers in collaboration with scientists from Denmark and Germany, AILA moves beyond the conventional role of AI models such as ChatGPT, which primarily assist with writing, analysis and data interpretation. Instead, AILA is designed to “do science”, handling the entire experimental workflow inside a laboratory.
“AILA helps me with my daily experimental tasks and speeds up my research progress significantly,” said Indrajeet Mandal, the first author of the study and a PhD scholar at IIT Delhi. “Earlier, optimising microscope parameters for high-resolution, noise-free images would take an entire day. Now, the same task is completed in just seven to ten minutes,” he said.
The research focused on enabling AILA to operate the Atomic Force Microscope, which examines materials at nanoscale resolution. The AI agent can adjust parameters, respond to live feedback during experiments and interpret results on its own, capabilities that typically take researchers years to master.
“Previously, AI could help you write about science. Now it can actually do science, designing experiments, running them on real equipment, collecting data and interpreting results,” said professor NM Anoop Krishnan of IIT Delhi, one of the supervisors of the project.
Professor Nitya Nand Gosvami from IIT Delhi’s Department of Materials Science and Engineering highlighted the significance of the achievement. “Operating an Atomic Force Microscope requires deep understanding of nanoscale physics and real-time feedback control. The fact that AILA can autonomously perform these tasks represents a paradigm shift in experimental science,” he said.
