Hypothesis ranking is vital for automated scientific discovery, especially in cost-intensive, throughput-limited natural science domains. Current methods focus on pre-experiment ranking, relying solely on language model reasoning without empirical feedback. We introduce experiment-guided ranking, which prioritizes hypotheses based on feedback from prior tests. Due to the impracticality of real experiments, we propose a simulator grounded in domain-specific concepts that models hypothesis performance as a function of similarity to a hidden ground truth, perturbed by noise. Validated against 124 hypotheses with experimentally reported outcomes, the simulator approximates real results with consistent trend alignment. Although deviations exist, they mimic wet-lab noise, promoting more robust ranking strategies. We frame experiment-guided ranking as a sequential decision-making problem and propose an in-context reinforcement learning (ICRL) framework. Our LLM-based policy decomposes hypotheses into functional elements, clusters them by mechanistic roles, and prioritizes recombinations based on feedback. Experiments show our approach significantly outperforms pre-experiment baselines and strong ablations. Our toolkit, comprising the simulator and ICRL framework, enables systematic research on experiment-guided ranking, with the policy serving as a strong proof of concept.

Artificial Intelligence (AI) is the theory and development of computer systems that are capable of performing tasks that require human intelligence; in other words, taking elements of what we today consider to be exclusively human traits and transferring them to a machine in a satisfactory manner. These human traits include visual perception, voice recognition, decision making, and translation. In addition, communication, the ability to learn new things, the ability to abstract or associate with new knowledge based on already established knowledge, and a number of other issues are key to the development of artificial intelligence. The machines should also have the same knowledge that we learn in school: the difference between right and wrong. How and what artificial intelligence will be used for in the future is still a question we don't know the answer to.

The pandemic has flipped the script on what skills are ‘valuable’ in the workforce - and forced individuals to rethink how to invest in their ‘skills equity’. The pandemic has also compounded the urgency with which the workforce has adopted a ‘skills-first’ approach to professional development. Seemingly overnight, it was no longer enough to acknowledge the importance of prioritising skills development without proactively doing something about it. The rise of remote work, mass closures, organisational shifts, and phenomena like “the great resignation” or the “she-cession,” have further demonstrated just how quickly the working world can change and force our collective hand to change. But as overwhelming as the change can feel, it’s important to remember that in change lies opportunity. Developing skills that take change head-on will determine who thrives in a new landscape.