Recent advancements in lab automation and machine learning have transformed organic chemistry. Closed-loop systems can autonomously design and execute experiments, leading to increased productivity. At the same time, machine learning can capture complex underlying relationships, guide decision-making, and enable accelerated discovery. However, to further enhance optimization performance, the integration of human expertise and prior knowledge could be leveraged. This can be achieved through hybrid human–AI approaches that combine the strengths of both humans and machines, through human-in-the-loop optimization that leverages the insights of experienced chemists or transfers learning from previous optimization campaigns. These approaches can help the system find promising regions of the search space more efficiently and handle unanticipated situations, making success more probable.

This thematic issue aims to explore recent advances in adaptive experimentation, automation, and synergetic human–AI approaches in organic chemistry. The focus will be on how these approaches can improve the efficiency and quality of research and accelerate the discovery of new molecules and reactions. The topics of interest include, but are not limited to:

• AI tools for the discovery of new molecules and reactions
• Intelligent automated discovery (exploration of chemical space, symbolic regression, etc.)
• High-throughput experimentation (validation and optimization of experiments, design and implementation of closed-loop systems, automation and robotics for self-driving labs and flow chemistry, etc.)
• Optimization algorithms for closed-loop experimentation systems (Bayesian optimization, reinforcement learning, model-based design of experiments, etc.)
• Integration of human expertise in automation processes (development of hybrid human–AI approaches)