# CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution

arXiv: https://arxiv.org/abs/2512.23880 · HTML: https://mlsanity.com/paper/2512.23880/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 41 of its 111 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 41)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields](https://mlsanity.com/paper/2206.07697/) (2022)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)
- [CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets](https://mlsanity.com/paper/2309.17428/) (2023)
- [Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution](https://mlsanity.com/paper/2505.20286/) (2025)
- [Kosmos: An AI Scientist for Autonomous Discovery](https://mlsanity.com/paper/2511.02824/) (2025)
- [Robin: A multi-agent system for automating scientific discovery](https://mlsanity.com/paper/2505.13400/) (2025)
- [Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models](https://mlsanity.com/paper/2410.12771/) (2024)
- [AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents](https://mlsanity.com/paper/2502.05957/) (2025)
- [LLM Agents Making Agent Tools](https://mlsanity.com/paper/2502.11705/) (2025)
- [SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?](https://mlsanity.com/paper/2507.05241/) (2025)
- [El Agente: An Autonomous Agent for Quantum Chemistry](https://mlsanity.com/paper/2505.02484/) (2025)
- [SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration](https://mlsanity.com/paper/2507.20280/) (2025)
- [CACTUS: Chemistry Agent Connecting Tool-Usage to Science](https://mlsanity.com/paper/2405.00972/) (2024)
- [ToolUniverse: An open platform for democratizing AI scientists](https://mlsanity.com/paper/2509.23426/) (2025)
- [Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents](https://mlsanity.com/paper/2509.06917/) (2025)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [The Denario project: Deep knowledge AI agents for scientific discovery](https://mlsanity.com/paper/2510.26887/) (2025)

## Built on by (most cited first, 30 of 34)

- [A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2605.07358/) (2026)
- [SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution](https://mlsanity.com/paper/2605.18401/) (2026)
- [SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents](https://mlsanity.com/paper/2605.18693/) (2026)
- [Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents](https://mlsanity.com/paper/2604.15877/) (2026)
- [Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2604.20987/) (2026)
- [Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond](https://mlsanity.com/paper/2604.22748/) (2026)
- [OpenSkill: Open-World Self-Evolution for LLM Agents](https://mlsanity.com/paper/2606.06741/) (2026)
- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries](https://mlsanity.com/paper/2605.19576/) (2026)
- [AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation](https://mlsanity.com/paper/2605.28655/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [Skill Coverage: A Test Adequacy Metric for Agent Skills](https://mlsanity.com/paper/2606.20659/) (2026)
- [MADE: Benchmark Environments for Closed-Loop Materials Discovery](https://mlsanity.com/paper/2601.20996/) (2026)
- [Co-Evolving Skill Generation and Policy Optimization](https://mlsanity.com/paper/2606.08755/) (2026)
- [Agentic LLM Reasoning in a Self-Driving Laboratory for Air-Sensitive Lithium Halide Spinel Conductors](https://mlsanity.com/paper/2604.11957/) (2026)
- [Harnessing AtomisticSkills for Agentic Atomistic Research](https://mlsanity.com/paper/2605.24002/) (2026)
- [Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries](https://mlsanity.com/paper/2607.10113/) (2026)
- [TritonDFT: Automating DFT with a Multi-Agent Framework](https://mlsanity.com/paper/2603.03372/) (2026)
- [El Agente Gr'afico: A Semantic Execution Runtime for Scientific Agents](https://mlsanity.com/paper/2602.17902/) (2026)
- [SwarmWorld: Stigmergic technological evolution in societies of language-model agents](https://mlsanity.com/paper/2608.26081/) (2026)
- [Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training](https://mlsanity.com/paper/2603.00454/) (2026)
- [Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research](https://mlsanity.com/paper/2603.28986/) (2026)
- [Towards Knowledgeable Deep Research: Framework and Benchmark](https://mlsanity.com/paper/2604.07720/) (2026)
- [The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents](https://mlsanity.com/paper/2607.07436/) (2026)
- [Harnessing agent memory to build lifelong AI partners for materials scientists](https://mlsanity.com/paper/2608.11224/) (2026)
- [Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents](https://mlsanity.com/paper/2609.18598/) (2026)
- [SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks](https://mlsanity.com/paper/2605.09038/) (2026)
- [DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning](https://mlsanity.com/paper/2605.23939/) (2026)
- [Harnessing X-ray Absorption Spectroscopy Data through Multimodal Mining of Battery Literature](https://mlsanity.com/paper/2607.23886/) (2026)
- [Quo Vadis, World Modeling?](https://mlsanity.com/paper/2608.02713/) (2026)

## Abstract (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.