The (R)evolution of Scientific Workflows in the Agentic AI Era: Towards Autonomous Science
This addresses the challenge for researchers who are burdened by manual workflow management, offering a transformative vision for scientific discovery, though it is conceptual and incremental in implementation.
The paper tackles the problem of manual coordination in scientific workflows by proposing a conceptual framework and architectural blueprint for integrating AI agents, aiming to enable fully autonomous, distributed scientific laboratories with potential for 100x acceleration in discovery.
Modern scientific discovery increasingly requires coordinating distributed facilities and heterogeneous resources, forcing researchers to act as manual workflow coordinators rather than scientists. Advances in AI leading to AI agents show exciting new opportunities that can accelerate scientific discovery by providing intelligence as a component in the ecosystem. However, it is unclear how this new capability would materialize and integrate in the real world. To address this, we propose a conceptual framework where workflows evolve along two dimensions which are intelligence (from static to intelligent) and composition (from single to swarm) to chart an evolutionary path from current workflow management systems to fully autonomous, distributed scientific laboratories. With these trajectories in mind, we present an architectural blueprint that can help the community take the next steps towards harnessing the opportunities in autonomous science with the potential for 100x discovery acceleration and transformational scientific workflows.