# Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments

arXiv: https://arxiv.org/abs/2602.16653 · HTML: https://mlsanity.com/paper/2602.16653/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

## Builds on (most cited first, 20 of 20)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness](https://mlsanity.com/paper/2411.03350/) (2024)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale](https://mlsanity.com/paper/2601.10338/) (2026)
- [MemInsight: Autonomous Memory Augmentation for LLM Agents](https://mlsanity.com/paper/2503.21760/) (2025)
- [Meta Context Engineering via Agentic Skill Evolution](https://mlsanity.com/paper/2601.21557/) (2026)
- [Exploring the Impact of Temperature on Large Language Models:Hot or Cold?](https://mlsanity.com/paper/2506.07295/) (2025)
- [When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail](https://mlsanity.com/paper/2601.04748/) (2026)
- [CUA-Skill: Develop Skills for Computer Using Agent](https://mlsanity.com/paper/2601.21123/) (2026)
- [Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?](https://mlsanity.com/paper/2306.01220/) (2023)
- [DENIAHL: In-Context Features Influence LLM Needle-In-A-Haystack Abilities](https://mlsanity.com/paper/2411.19360/) (2024)
- [Small Language Models in the Real World: Insights from Industrial Text Classification](https://mlsanity.com/paper/2505.16078/) (2025)

## Built on by (most cited first, 3 of 3)

- [SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models](https://mlsanity.com/paper/2608.10538/) (2026)
- [SkillEval: Decomposing Agent Skill Quality into Interpretable Signals](https://mlsanity.com/paper/2608.06891/) (2026)
- [Compression, structure, and executor capability: a controlled real-cost decomposition of language-model agent skill optimisation](https://mlsanity.com/paper/2607.03048/) (2026)

## Abstract (arXiv)

Skills are getting increasingly used in recent agentic frameworks, performing robustly with proprietary LLMs. Yet, their effectiveness for small and medium-sized open-source models (270M--80B) remains underexplored, especially under industrial, resource-constrained conditions. As such, we present a large-scale empirical study evaluating the skill paradigm's feasibility across two open-source classification tasks: one insurance-claim task based on proprietary data, and a set of Python programming problems. We find that very small models frequently fail to retrieve or select correct skills, substantially limiting their usefulness in the evaluated skill-augmented settings, while larger 30B--80B models gain substantial benefits from skill augmentation. Furthermore, we provide a deployment-oriented GPU profile, reporting VRAM time occupancy (GB·min) across models under our evaluation settings---a deployment-oriented metric that may help characterize GPU-memory costs, where small and medium models are typically preferred for VRAM control. These results characterize how the benefits of skill augmentation vary with model scale, task complexity, and GPU budget, and provide deployment-oriented observations.