Researchers have proposed a new framework called MAPPS (Materials Agent unifying Planning, Physics, and Scientists) to improve the autonomy of language agents in discovering crystal materials. MAPPS consists of three components: a Workflow Planner that generates structured workflows using large language models, a Tool Code Generator that synthesizes executable code for various tasks, and a Scientific Mediator that coordinates communications between scientists and ensures robustness. The framework enables flexible and reliable materials discovery with greater autonomy, achieving a five-fold improvement in stability, uniqueness, and novelty rates compared to prior generative models. --- Why it matters: This matters because it could accelerate the development of new materials by automating the workflow planning process, allowing researchers to focus on high-level goals rather than specific tasks. This could lead to breakthroughs in fields like energy storage, electronics, or biomedical applications. Source: https://arxiv.org/abs/2506.05616