OECD Digital Education Outlook 2026: Exploring Effective Uses of Generative AI in Education

The AI systems examined above keep to the cognitive tasks of research: analysing and generating information. Other systems go one step further and aim at performing the whole range of tasks of a research assistant, notably the design of experiments (research assistants), or even the realisation of experiments (robot scientists).

There has been a surge in the supply of AI research assistants since 2024 (see Box 13.4). They can be compared to the teaching assistants described by Baker et al. (2026), even though their functionalities and workings are different. The characteristics shared by AI research assistants are the following: 1) they perform all tasks expected from a research assistant: reviewing literature, generating hypotheses, designing experiments, drafting articles; 2) they are technically similar to the hypothesis generation models examined above (multi-agents, etc.); 3) they are very interactive, as their functioning involves frequent and important exchanges with a supervising human, who remains in close control of the research process; they are just “assistants” after all.

According to So (2025), AI research assistants offer numerous benefits, including accelerated research timelines, 24/7 availability, personalised support, enhanced objectivity and improved accessibility for non-native English speakers. AI research assistants are evolving to support various collaboration models, from passive assistants to full research partners. Despite their impressive capabilities, AI research assistants face significant challenges, including generating inaccurate information, limitations in critical analysis, and ethical concerns around plagiarism and attribution.

The system autonomously identifies new research problems, proposes methods and designs experiments, refining them through feedback from LLM-based reviewing agents. Beginning with a core scientific paper, ResearchAgent expands its scope by linking related publications through an academic graph and incorporating concepts extracted from a knowledge base built across many papers. Emulating peer review, it uses multiple LLM Reviewing Agents that provide critiques and iterative revisions. These agents are aligned with human preferences, with their evaluation criteria derived from real human judgments through LLM prompting.

The system is built around specialised agents that collaborate across different phases of research. During the experimentation phase, PhD and Postdoc agents design the research plan, while machine learning and software engineer agents handle data preparation and coding tasks. An automated module then generates, tests and iteratively improves machine learning code. It also includes an LLM-driven repair function to correct errors during execution. In the report writing phase, Professor and PhD agents compile the results into a structured report. This process mirrors peer review, with iterative revisions and checkpoints that can be autonomous or human-guided.

The “robot scientist” marks the automation of the last step in the research cycle, the performance of experiments. The robot scientist works by connecting laboratory equipment to an AI system: the AI designs the experiments and controls the equipment so that it performs these experiments.

Why automate experiments? Here is one example. According to pioneer Ross King (2024):

Studying eukaryotic system biology is a complicated task as even simple eukaryotic cells such as yeast have thousands of genes, proteins, and other small molecules, that interact in a complex spatial and temporal manner. The high complexity of the models means that their development and evaluation require the execution of millions of experiments based on a hypothesis. Only AI systems with automated labs have the capacity to plan, conduct, and monitor such a high number of experiments.

In this case, the robot allows researchers to perform experiments that would be beyond human capabilities. An additional advantage of robot labs is that their experiments generate large quantities of high-quality, controlled data that can be used to train AI models.

One example in chemistry is CRESt (Ren et al., 2023): users exchange with CRESt like with a colleague, in natural language. CRESt helps to craft and run experiments by retrieving and analysing data, turning equipment on and off, powering robotic arms, documenting findings and alerting scientists when something requiring their attention arises. CRESt-assisted researchers identified candidate alloys for fuel cells.

While important for many scientific fields, the automation of laboratory work seems less relevant for education research, where most of the experiments involve humans in a controlled or real-life environment. This may however support work about chemistry, biology or neuroscience that will help understand how human learns or where some impediments can come from.

Synthesis

Table 13.1 presents a summary of the possible roles of GenAI at the different steps of the research process, as well as their current achievements and limitations.