{"ID":2824519,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.23880","arxiv_id":"2512.23880","title":"CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution","abstract":"Large language model (LLM) agents currently depend on predefined tools or early-stage tool generation, limiting their adaptability and scalability 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, code extraction, and memory utilization; self-reflection via introspection, knowledge graph exploration, and 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.","short_abstract":"Large language model (LLM) agents currently depend on predefined tools or early-stage tool generation, limiting their adaptability and scalability 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 + sk...","url_abs":"https://arxiv.org/abs/2512.23880","url_pdf":"https://arxiv.org/pdf/2512.23880v2","authors":"[\"Xu Huang\",\"Junwu Chen\",\"Yuxing Fei\",\"Zhuohan Li\",\"Philippe Schwaller\",\"Gerbrand Ceder\"]","published":"2025-12-29T21:50:23Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cond-mat.mtrl-sci\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}