SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
Summary
This paper introduces SkillLens, a hierarchical framework for adaptive multi-granularity skill reuse in LLM agents, demonstrating improved accuracy and cost-efficiency on benchmark tasks.
View Cached Full Text
Cached at: 05/12/26, 07:11 AM
# SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents Source: [https://arxiv.org/abs/2605.08386](https://arxiv.org/abs/2605.08386) [View PDF](https://arxiv.org/pdf/2605.08386) > Abstract:Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks\. However, existing systems typically treat skills as flat, single\-resolution prompt blocks\. This creates a tension between relevance and cost: injecting coarse skills can introduce irrelevant or misleading context, while rewriting entire skills is expensive and often unnecessary\. We propose SkillLens, a hierarchical skill\-evolution framework that organizes skills into a four\-layer graph of policies, strategies, procedures, and primitives, and retrieves them at mixed granularity\. Given a task, SkillLens first retrieves semantically relevant skill seeds, expands them through degree\-corrected random walk over the skill graph, and then uses a verifier to decide whether each visited unit should be accepted, decomposed, rewritten, or skipped\. This enables the agent to reuse compatible subskills directly while adapting only locally mismatched components\. To improve the system over time, SkillLens further refines multi\-granularity skills and verifier in order to improve its routing decisions\. We provide theoretical analysis showing that mixed\-granularity adaptation incurs sublinear cost under sparse mismatch assumptions and that the evolutionary update rule monotonically improves the validation objective until a local optimum\. Across MuLocbench and ALFWorld, SkillLens consistently improves over strong skill\-based baselines, achieving up to a 6\.31 percentage\-point Acc@1 gain for bug localization and raising agent success rate from 45\.00% to 51\.31%\. ## Submission history From: Ziyang Yu \[[view email](https://arxiv.org/show-email/cef65bae/2605.08386)\] **\[v1\]**Fri, 8 May 2026 18:48:04 UTC \(93 KB\)
Similar Articles
SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
This paper introduces SkillMaster, a training framework that enables LLM agents to autonomously create, refine, and select skills through trajectory-informed review and counterfactual utility evaluation.
SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
This paper introduces SkillRet, a large-scale benchmark for evaluating skill retrieval in LLM agents, addressing the challenge of selecting relevant skills from large libraries. It provides a dataset of over 17,000 skills and demonstrates that task-specific fine-tuning significantly improves retrieval performance.
SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
SkillLearnBench introduces the first benchmark for evaluating continual skill learning in LLM agents across 20 real-world tasks, revealing that no method dominates and scaling LLMs does not guarantee better skills.
SkillOS: Learning Skill Curation for Self-Evolving Agents
This paper introduces SkillOS, a reinforcement learning framework that enables LLM agents to learn long-term skill curation policies for self-evolution, improving performance and generalization across tasks.
SkillGen: Verified Inference-Time Agent Skill Synthesis
This article introduces SkillGen, a multi-agent framework that synthesizes and verifies reusable inference-time skills for LLM agents by contrasting successful and failed trajectories. The method ensures skills are auditable and empirically verified for their net positive impact on agent performance.