# SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?

arXiv: https://arxiv.org/abs/2603.00718 · HTML: https://mlsanity.com/paper/2603.00718/

## Key facts

- Cited by 30 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 25 of its 36 references that are in the map.
- First posted on arXiv 28 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, 25 of 25)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory](https://mlsanity.com/paper/2305.17144/) (2023)
- [CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models](https://mlsanity.com/paper/2305.14318/) (2023)
- [The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution](https://mlsanity.com/paper/2510.25726/) (2025)
- [SWE-bench Goes Live!](https://mlsanity.com/paper/2505.23419/) (2025)
- [ACEBench: Who Wins the Match Point in Tool Usage?](https://mlsanity.com/paper/2501.12851/) (2025)
- [MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers](https://mlsanity.com/paper/2602.00933/) (2026)
- [MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models](https://mlsanity.com/paper/2505.16700/) (2025)
- [LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?](https://mlsanity.com/paper/2508.01780/) (2025)
- [MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents](https://mlsanity.com/paper/2506.07672/) (2025)
- [MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models](https://mlsanity.com/paper/2507.12806/) (2025)
- [MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools](https://mlsanity.com/paper/2509.09734/) (2025)
- [ARE: Scaling Up Agent Environments and Evaluations](https://mlsanity.com/paper/2509.17158/) (2025)

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

- [CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification](https://mlsanity.com/paper/2604.01687/) (2026)
- [Natural-Language Agent Harnesses](https://mlsanity.com/paper/2603.25723/) (2026)
- [SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision](https://mlsanity.com/paper/2606.01139/) (2026)
- [SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents](https://mlsanity.com/paper/2604.17308/) (2026)
- [From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills](https://mlsanity.com/paper/2605.23899/) (2026)
- [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)
- [Skill-R1: Agent Skill Evolution via Reinforcement Learning](https://mlsanity.com/paper/2605.09359/) (2026)
- [SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement](https://mlsanity.com/paper/2606.10546/) (2026)
- [WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution](https://mlsanity.com/paper/2608.27454/) (2026)
- [SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology](https://mlsanity.com/paper/2604.17503/) (2026)
- [SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents](https://mlsanity.com/paper/2606.13317/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries](https://mlsanity.com/paper/2607.10113/) (2026)
- [SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills](https://mlsanity.com/paper/2605.24117/) (2026)
- [TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows](https://mlsanity.com/paper/2608.02680/) (2026)
- [RedAct: Redacting Agent Capability Traces for Procedural Skill Protection](https://mlsanity.com/paper/2606.10813/) (2026)
- [Tools as Continuous Flow for Evolving Agentic Reasoning](https://mlsanity.com/paper/2605.07339/) (2026)
- [Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning](https://mlsanity.com/paper/2606.00510/) (2026)
- [OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models](https://mlsanity.com/paper/2606.16774/) (2026)
- [Coalition-Aware Skill Reliability for Self-Evolving Agents](https://mlsanity.com/paper/2608.22610/) (2026)
- [Evidence Over Plans: Online Trajectory Verification for Skill Distillation](https://mlsanity.com/paper/2605.09192/) (2026)
- [SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?](https://mlsanity.com/paper/2605.26186/) (2026)
- [PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents](https://mlsanity.com/paper/2605.08468/) (2026)
- [Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning](https://mlsanity.com/paper/2608.05139/) (2026)
- [Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution](https://mlsanity.com/paper/2608.21341/) (2026)
- [Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security](https://mlsanity.com/paper/2608.29596/) (2026)
- [Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2609.09233/) (2026)
- [RESKILL: Explicit Failure Attribution and Structured Repair for Interactive Language Agents](https://mlsanity.com/paper/2609.15684/) (2026)
- [EVISKILL: Grounding Skill Evolution in Replayable Evidence](https://mlsanity.com/paper/2610.05030/) (2026)

## Abstract (arXiv)

Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but also abstracting, and reusing higher-level tool compositions. However, existing benchmarks mainly measure instance-level success under static tool sets, offering limited insight into agents' ability to acquire such reusable skills. We address this gap by introducing SkillCraft, a benchmark explicitly stress-test agent ability to form and reuse higher-level tool compositions, where we call Skills. SkillCraft features realistic, highly compositional tool-use scenarios with difficulty scaled along both quantitative and structural dimensions, designed to elicit skill abstraction and cross-task reuse. We further propose a lightweight evaluation protocol that enables agents to auto-compose atomic tools into executable Skills, cache and reuse them inside and across tasks, thereby improving efficiency while accumulating a persistent library of reusable skills. Evaluating state-of-the-art agents on SkillCraft, we observe substantial efficiency gains, with token usage reduced by up to 80% by skill saving and reuse. Moreover, success rate strongly correlates with tool composition ability at test time, underscoring compositional skill acquisition as a core capability.