Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning

arXiv:2606.00510 · cs.CL, cs.AI · Submitted 2026-05-30 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-05-30

Updated: 2026-08-31

Comments: 17 pages, 4 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 33× in this paper · explained in 2 episodes
• GRPO — 12× in this paper · explained in 6 episodes
• Agent Skills — 8× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Agentic Task — 5× in this paper · explained in 1 episode
• Agentic Tasks — 5× in this paper · explained in 1 episode
• Robustness — 5× in this paper · explained in 5 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Direct Preference Optimization — 2× in this paper
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Agentic Evaluation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
• SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
• Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
• Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• Agentic Reinforced Policy Optimization
• SkillOS: Learning Skill Curation for Self-Evolving Agents
• SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• SkillNet: Create, Evaluate, and Connect AI Skills
• Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
• Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
• SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
• How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
• Qwen3 Technical Report
• AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
• Skill Retrieval Augmentation for Agentic AI

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering