## Introduction Meta announced today a new breakthrough for Large Language Models (LLMs): CASCADE enables autonomous development and evolution. Current LLMs rely on predefined tools or brittle tool generation, constraining their capability and adaptability to complex scientific tasks. We introduce CASCADE, a self-evolving agentic framework representing an early instantiation of the transition from 'LLM + tool use' to 'LLM + skill acquisition'. CASCADE enables agents to master complex external tools and codify knowledge through two meta-skills: continuous learning via web search and code extraction, and self-reflection via introspection and knowledge graph exploration, among others. We evaluate CASCADE on SciSkillBench, a benchmark of 116 materials science and chemistry research tasks. CASCADE achieves a 93.3% success rate using GPT-5, compared to 35.4% without evolution mechanisms. We further demonstrate real-world applications in computational analysis, autonomous laboratory experiments, and selective reproduction of published papers. Along with human-agent collaboration and memory consolidation, CASCADE accumulates executable skills that can be shared across agents and scientists, moving toward scalable AI-assisted scientific research.