Tag
This paper presents an agent-based system within the URSA framework that autonomously designs, executes, and validates atomistic simulations using LAMMPS, reducing manual intervention and improving reproducibility.
This article details the new paradigm of AI for Science (AI4S), from AI as an analysis tool to the transition to scientific agents, explaining autonomy levels, key cases, and future trends.
This paper introduces AgentBuild, a framework for constructing LLM-based scientific agents using a scientist-authored contract that includes a rubric, curriculum, and knowledge base. It demonstrates this for Rietveld refinement of X-ray diffraction data, showing how the agent can be built and tuned.