How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

• URL: http://arxiv.org/abs/2604.04323v1
• Date: Mon, 06 Apr 2026 00:10:30 GMT
• Title: How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
• Abstract summary: We study the first comprehensive study of skill utility under progressively challenging realistic settings.<n>Our findings reveal that performance gains degrade consistently as settings become more realistic.<n>We show that query-specific refinement substantially recovers lost performance when the initial skills are of reasonable relevance and quality.
• Score: 29.3744517703302
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts focus on overly idealized conditions, where LLMs are directly provided with hand-crafted, narrowly-tailored task-specific skills for each task, whereas in many realistic settings, the LLM agent may have to search for and select relevant skills on its own, and even the closest matching skills may not be well-tailored for the task. In this paper, we conduct the first comprehensive study of skill utility under progressively challenging realistic settings, where agents must retrieve skills from a large collection of 34k real-world skills and may not have access to any hand-curated skills. Our findings reveal that the benefits of skills are fragile: performance gains degrade consistently as settings become more realistic, with pass rates approaching no-skill baselines in the most challenging scenarios. To narrow this gap, we study skill refinement strategies, including query-specific and query-agnostic approaches, and we show that query-specific refinement substantially recovers lost performance when the initial skills are of reasonable relevance and quality. We further demonstrate the generality of retrieval and refinement on Terminal-Bench 2.0, where they improve the pass rate of Claude Opus 4.6 from 57.7% to 65.5%. Our results, consistent across multiple models, highlight both the promise and the current limitations of skills for LLM-based agents. Our code is available at https://github.com/UCSB-NLP-Chang/Skill-Usage.

Related papers

• Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents [67.97365535829098]
  Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.<n>We propose Evo-Harness, which distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation.<n>Our analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly.
  arXiv  Detail & Related papers  (2026-08-15T06:43:56Z)
• Parametric Skills [18.083331448567936]
  ParametricSkills is a framework that can convert free-form textual skills into parameters at test time, enabling context-free skill exploitation.<n>We show that, the proposed ParametricSkills averagely outperforms in-context learning by 6.44 points as judged by DeepSeek-V4-Flash.
  arXiv  Detail & Related papers  (2026-06-29T09:19:32Z)
• A Framework for Evaluating Agentic Skills at Scale [0.4509560087514856]
  Agent skills are structured, reusable knowledge artifacts that augment agent capabilities.<n>No reusable methodology exists for evaluating an individual skill.<n>We present an evaluation framework that lets a skill author construct realistic tasks.
  arXiv  Detail & Related papers  (2026-06-16T11:46:56Z)
• SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization [99.18305770138677]
  Agent skills are reusable strategies that guide agent reasoning and action.<n>Current skill construction methods treat the problem as one-shot extraction.<n>We introduce SkillComposer, a framework that decomposes skill construction into three learnable operations.
  arXiv  Detail & Related papers  (2026-06-04T12:16:08Z)
• SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision [41.562357872885826]
  We propose SkillRevise, an execution-grounded framework designed to iteratively refine agent skills.<n>SkillRevise diagnoses skill defects from execution evidence, retrieves relevant repair principles from a general memory, and applies execution-anchored edits.<n>It substantially outperforms one-shot baselines, improving the base agent's success rate on SkillsBench from 36.05% to 61.63%.
  arXiv  Detail & Related papers  (2026-05-31T10:19:13Z)
• Skill-R1: Agent Skill Evolution via Reinforcement Learning [84.35984979949502]
  Skill-R1 is a reinforcement learning framework for instance-level recurrent skill optimization from verifiable rewards.<n>It preserves black-box compatibility with both open- and closed-source models while making adaptation substantially cheaper than model-level updates.
  arXiv  Detail & Related papers  (2026-05-10T06:19:15Z)
• SkillGen: Verified Inference-Time Agent Skill Synthesis [60.927977774369516]
  SkillGen is a framework that synthesizes a single auditable skill from trajectories generated by a base agent.<n>It identifies reusable success patterns, recurring failure modes, and behaviors that appear in nearby successes but are missing from failures.<n>A key novelty in SkillGen is that we model agent skills as interventions to empirically verify the net effect of skills on the overall performance.
  arXiv  Detail & Related papers  (2026-05-09T19:24:11Z)
• SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents [6.293920920196533]
  SkillLens is a hierarchical skill-evolution framework that organizes skills into a four-layer graph of policies, strategies, procedures, and primitives.<n>It 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.<n>Across MuLocbench and ALFWorld, SkillLens consistently improves over strong skill-based baselines.
  arXiv  Detail & Related papers  (2026-05-08T18:48:04Z)
• SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents [8.628588436048952]
  We introduce SkillRet, a large-scale benchmark for skill retrieval in LLM agents.<n>It provides 63,259 training samples and 4,997 evaluation queries with disjoint skill pools.<n>Off-the-shelf models struggle on realistic large-scale skill libraries, and prior skill-retrieval models still leave substantial headroom.
  arXiv  Detail & Related papers  (2026-05-07T06:18:11Z)
• SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization [61.37478254738943]
  Inference-time skill augmentation is fundamentally limited.<n>We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization.<n>SKILL0 achieves substantial improvements over the standard RL baseline.
  arXiv  Detail & Related papers  (2026-04-02T17:03:05Z)
• EvoSkill: Automated Skill Discovery for Multi-Agent Systems [6.319876096746374]
  We introduce textbfEvoSkill, a self-evolving framework that automatically discovers and refines agent skills.<n>EvoSkill analyzes execution failures, proposes new skills or edits to existing ones, and materializes them into structured, reusable skill folders.<n>We evaluate EvoSkill on two benchmarks: OfficeQA, a grounded reasoning benchmark over U.S. Treasury data, and SealQA, a noisy retrieval benchmark.
  arXiv  Detail & Related papers  (2026-03-03T09:07:22Z)
• SkillCraft: Can LLM Agents Learn to Use Tools Skillfully? [67.69996753743129]
  We introduce SkillCraft, a benchmark explicitly stress-test agent ability to form and reuse higher-level tool compositions.<n> SkillCraft features realistic, highly compositional tool-use scenarios with difficulty scaled along both quantitative and structural dimensions.<n>We propose a lightweight evaluation protocol that enables agents to auto-compose atomic tools into executable Skills, cache and reuse them inside and across tasks.
  arXiv  Detail & Related papers  (2026-02-28T15:44:31Z)
• Reinforcement Learning for Self-Improving Agent with Skill Library [14.717149089634718]
  Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions.<n>One promising approach is implementing skill libraries that allow agents to learn, validate, and apply new skills.<n>We propose a Reinforcement Learning (RL)-based approach to enhance agents' self-improvement capabilities with a skill library.
  arXiv  Detail & Related papers  (2025-12-18T21:58:19Z)
• Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives [54.14429346914995]
  Chain-of-Thought (CoT) has become a pivotal method for solving complex problems with large language models (LLMs)<n>This paper introduces the Re-TASK framework, a novel theoretical model that revisits LLM tasks from capability, skill, and knowledge perspectives.<n> Experiments across diverse domains demonstrate the effectiveness of Re-TASK.
  arXiv  Detail & Related papers  (2024-08-13T13:58:23Z)
• Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts [58.220879689376744]
  Reinforcement learning (RL) is a powerful approach for acquiring a good-performing policy. We propose textbfDiverse textbfSkill textbfLearning (Di-SkilL) for learning diverse skills. We show on challenging robot simulation tasks that Di-SkilL can learn diverse and performant skills.
  arXiv  Detail & Related papers  (2024-03-11T17:49:18Z)
• Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics [18.546688182454236]
  Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. We propose accelerating exploration in the skill space using state-conditioned generative models. We validate our approach across four challenging manipulation tasks, demonstrating our ability to learn across task variations.
  arXiv  Detail & Related papers  (2022-11-04T02:42:17Z)
• Design of Negative Sampling Strategies for Distantly Supervised Skill Extraction [19.43668931500507]
  We propose an end-to-end system for skill extraction, based on distant supervision through literal matching. We observe that using the ESCO taxonomy to select negative examples from related skills yields the biggest improvements. We release the benchmark dataset for research purposes to stimulate further research on the task.
  arXiv  Detail & Related papers  (2022-09-13T13:37:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.