Here, Nature explores how academics and students can harness AI to streamline various parts of the research process.<\/p>\n
Sharpen your literature review<\/b><\/p>\n
Daniel Weld, chief scientist at the academic search engine Semantic Scholar, who is based in Seattle, Washington, says that many popular AI platforms have \u201cadvanced enormously\u201d in an area called active learning \u2014 a method that mimics how a person would approach a research question. Programs such as Google\u2019s Gemini Deep Research<\/a> and OpenAI\u2019s Deep Research<\/a> offer the most powerful tools in this regard, and many companies are launching similar products.<\/p>\n Students can enter a query, supported by their own data or documents, and then step away as these advanced models conduct in-depth searches over 30 minutes or so. The final report might include text, figures and visualizations, and all output is thoroughly referenced \u2014 another jump over past iterations, says Isa Fulford, a technical staff researcher at OpenAI in San Francisco, California, who helped to develop Deep Research. \u201cEspecially in the context of scientific research, we recognize that veracity is critical, and we think this model is better at including the proper citations than any other model we\u2019ve released,\u201d she says.<\/p>\n Chuck Downing, a PhD student in accounting at the Massachusetts Institute of Technology (MIT) in Cambridge, says that these deep-research tools have been especially useful when digging into unfamiliar topics. During one project, Downing used OpenAI\u2019s Deep Research to create a report ranking various approaches for reducing emissions at manufacturing plants. \u201cI didn\u2019t know much going in, but I learnt quite a bit, and so I use these deep dives all the time now,\u201d he says. \u201cIt\u2019s better than anything else I\u2019ve used so far at finding good papers and in presenting the information in a way that I can easily understand.\u201d<\/p>\n Other programs enable students to delve more deeply into a single document or small collection of papers. The student-focused AI platform SciSpace<\/a> , for example, has a \u2018Chat with PDF\u2019 function. Users can upload a paper and ask questions about its content \u2014 a feature shared by other platforms, such as Claude<\/a>, NotebookLM<\/a> and PDF.ai<\/a>.<\/p>\n For David Tompkins, a PhD student in human development at Cornell University in Ithaca, New York, this approach has helped him to stay on top of the burgeoning scientific literature. Tompkins often goes to journal-club meetings having used Claude to generate a summary of a chosen paper, which he then follows up with more-targeted questions based on the group\u2019s discussion. \u201cI\u2019m still a big believer in actually reading papers to fully understand them, but it\u2019s become much easier to do my prep when I\u2019m feeling stretched,\u201d he says. \u201cIn some ways, I feel I\u2019m engaging more with the material through these tools than I did before them.\u201d<\/p>\n Create your hypothesis<\/b><\/p>\n The ability of AI to pull together many threads of information has seemingly made it easier to identify research gaps and connect ideas \u2014 although a recent survey<\/a> suggests that an over-reliance on generative AI could dampen a person\u2019s critical-thinking skills. Weld, who is also an AI researcher at the Allen Institute for AI in Seattle, says there has been so much demand for tools that assist with ideation that he and his team are developing hypothesis-generation and detection products that attempt to combine ideas across papers into something new. \u201cWe have them running internally, but we\u2019re trying to make sure that they\u2019re working robustly,\u201d he says, adding that his Allen Institute group hopes to release them publicly in the next few months.<\/p>\n Shafi turned to programs such as the visualization tool Research Rabbit<\/a> when working on his dissertation, which focuses on how microplastics are transported through soil and into groundwater. Research Rabbit takes a single \u2018seed paper\u2019 and generates an interconnected web of research linked by topic, author, methodology or other key features. By piping its results into a chatbot such as ChatGPT, \u201cit\u2019s possible to query the body of work for hidden links or new ideas\u201d, Shafi says.<\/p>\n Mar\u00eda Mercedes Hincapi\u00e9-Otero.Credit: Jayson J. Ricamara<\/p>\n AI-powered programs are also proving increasingly capable as experimental assistants. As a PhD student at MIT, Zhichu Ren created the software Copilot for Real-world Experimental Scientist (CRESt), which combines several AI technologies into an enhanced chatbot (Z. Ren et al. Preprint at ChemRxiv https:\/\/doi.org\/pdwv; 2023<\/a>). Users can chat with CRESt as they would with a colleague, and it can help to craft and run experiments by retrieving and analysing data, turning equipment on and off using digital switches, powering robotic arms, documenting findings and alerting scientists by e-mail when issues arise or protocols end<\/a>. In a 2023 conference paper,<\/a> CRESt assisted researchers by prioritizing candidate alloys for a new fuel cell, and suggested experiments that the group might run to test them. \u201cI wanted to create a tool that can continue to help even as your needs change,\u201d says Ren, who now works at the AI start-up firm Labig in Cambridge, Massachusetts. \u201cAI can do that in a way that static, written documentation cannot.\u201d<\/p>\n But even for students who do not have access to something as advanced as CRESt, AI can still function as a helpful colleague. Gemini Deep Research, for example, can generate a \u201cpersonalized multi-point research plan\u201d among other features, and resources such as Scite<\/a> and Elicit<\/a> are billed as research assistants. Users can give these programs a handful of papers or a working hypothesis, for example, and ask for a set of experiments to test the theory.<\/p>\n Joseph Fernandez, a PhD student in biomedical engineering at the University of Colorado Anschutz Medical Campus in Aurora, says he continues to use ChatGPT for most things, including troubleshooting his experiments. In the past, the bot has helped him to brainstorm explanations when one of his assays was returning unusual values, and to calculate serial dilutions to avoid wasting expensive reagents. ChatGPT has also served as a stand-in for his committee, generating pointed questions to test his research proposal before his exams.<\/p>\n \u201cI think you\u2019re really only limited by your imagination, even if some uses are more mundane than others,\u201d he says. \u201cNowadays, if a question or task pops into my mind, I\u2019m generally wondering if ChatGPT can help with it.\u201d<\/p>\n Streamline your statistics<\/b><\/p>\n Code editors including GitHub\u2019s Copilot<\/a>, Amazon CodeWhisperer<\/a> (now Amazon Q Developer) and Anysphere\u2019s Cursor<\/a> aim to make it easy for beginners to use coding to organize data, create analysis pipelines, run descriptive statistics and generate visualizations. Such tools, researchers note, have also largely overtaken websites such as GitHub and Stack Exchange as the main resources for troubleshooting. Rather than spending hours looking for answers, users can simply highlight a section of code and ask a chatbot to fix it, Downing says.<\/p>\n \u201cThinking about what a PhD student primarily does, the largest tasks are increasingly coding and data analysis, at least for computational fields, so anything that helps there is just disproportionately useful,\u201d he says. Although he already considered himself an adequate coder, he says that his preferred tool, Cursor, has made him better by removing the more tedious aspects and making it easier to probe specific aspects of a data set. Instead of spending all of his time debugging (cleaning the code), he says, he is \u201cputting more effort into really getting to know the underlying data and engaging with my code in ways that help me learn. If I get curious about something, it\u2019s very easy to generate descriptive statistics, something like a chart.\u201d<\/p>\n Tompkins has likewise found tools such as Claude to be essential for writing code for compelling, dynamic visualizations. Creating a good graph, particularly if it\u2019s interactive, can require hundreds of lines of code, and Tompkins says that, in the past, that level of effort had put him off. \u201cBut once I started using Claude, I was able to have it write out those literal hundreds of lines of code,\u201d he says. The resulting visualizations have gone a long way towards helping others to understand his research, which describes how small changes in the way in which people experience information can drive their reactions to it.<\/p>\n Researcher Zhichu Ren created an AI-based system called CRESt to run experiments.Credit: Jason Sparapani\/MIT Department of Materials Science and Engineering<\/p>\n He adds, however, that he still always writes his own code for statistical analyses: \u201cI want to make sure that whatever I\u2019m reporting is something that I fully understand and can stand behind when I submit a paper.\u201d<\/p>\n![\"A](\"https:\/\/www.europesays.com\/uk\/wp-content\/uploads\/2025\/04\/d41586-025-01069-0_50828164.jpg\"\/)
<\/p>\n![\"A](\"https:\/\/www.europesays.com\/uk\/wp-content\/uploads\/2025\/04\/d41586-025-01069-0_50828166.jpg\"\/)
<\/p>\n