CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution

2025-12-29 · Xu Huang, Junwu Chen, Yuxing Fei, Zhuohan Li, Philippe Schwaller, Gerbrand Ceder arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.23880

Code (0)

등록된 구현이 없습니다.

ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL

2026-06-01 · Zelin He, Haotian Lin, Boran Han, Wei Zhu 외 arxiv

Agentic reinforcement learning (RL) enables LLM agents to improve continuously from environment rewards, yet the resulting policies do not systematically accumulate reusable strategies that generalize across tasks. Modul…

Reinforcement Learning

SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning

2026-07-13 · Jinxiu Liu, Jianru Li, Tanqing Kuang, Xuanming Liu 외 arxiv

Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation. Yet prevailing monolithic models remain fundamentally constrained by their inability…

Continual Learning

Agent Skill Evaluation and Evolution: Frameworks and Benchmarks

2026-06-09 · Kexin Ding, Yang Zhou, Can Jin, Feng Tong 외 arxiv

The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety…

Reinforcement Learning

MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory

2026-05-08 · Yang Zhao, Chengxiao Dai, Mengying Kou, Yue Xiu arxiv

Agentic memory evolves across tasks into durable derived artifacts: summaries, cached outputs, embeddings, learned skills, and executable tool procedures. When a source artifact is deleted, corrected, or invalidated by t…

Dynamic Dual-Granularity Skill Bank for Agentic RL

2026-03-30 · Songjun Tu, Chengdong Xu, Qichao Zhang, Yaocheng Zhang 외 arxiv

Agentic RL can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We p…