Skill Blocks: How Should an Agent Load Its Skill? A Caching-Correct Comparison of Pre-load, On-Demand Tool-Loading, Progressive Disclosure, and Hybrid

[2608.14943] Skill Blocks: How Should an Agent Load Its Skill? A Caching-Correct Comparison of Pre-load, On-Demand Tool-Loading, Progressive Disclosure, and Hybrid Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.14943 (cs) [Submitted on 14 Aug 2026] Title: Skill Blocks: How Should an Agent Load Its Skill? A Caching-Correct Comparison of Pre-load, On-Demand Tool-Loading, Progressive Disclosure, and Hybrid Authors: Hironobu Nakasuji View a PDF of the paper titled Skill Blocks: How Should an Agent Load Its Skill? A Caching-Correct Comparison of Pre-load, On-Demand Tool-Loading, Progressive Disclosure, and Hybrid, by Hironobu Nakasuji View PDF HTML (experimental) Abstract: Agent skills are often injected in full on every request, increasing token cost. We compare four content-preserving loading methods: Full, Skill Block, Reference, and Hybrid. Across SearchQA, SpreadsheetBench, ALFWorld, ScienceWorld, and SynthProc, we measure token usage using raw input for single-turn tasks and cache-correct effective input for multi-turn tasks. Results show no universal winner. Hybrid reduces input by 27.4% on SearchQA and 39.8% on SpreadsheetBench. On large multi-turn skills, Skill Block and Hybrid achieve substantial reductions, reaching 62.5% and 52.8% on ScienceWorld and 73.0% and 66.6% on SynthProc. ALFWorld shows smaller gains because procedures are short and repeatedly needed. Paired outcome tests detect no quality differences, though they do not establish equivalence. Overall, conditional loading is most beneficial when large portions of a skill are not needed on every turn. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2608.14943 [cs.AI] (or arXiv:2608.14943v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.14943 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Hironobu Nakasuji [ view email ] [v1] Fri, 14 Aug 2026 23:48:09 UTC (24 KB) Full-text links: Access Paper: View a PDF of the paper titled Skill Blocks: How Should an Agent Load Its Skill? A Caching-Correct Comparison of Pre-load, On-Demand Tool-Loading, Progressive Disclosure, and Hybrid, by Hironobu Nakasuji View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents#1011382
• Effects of Rhodiola Rosea Supplementation on Mental Fatigue, Visuo-cognitive Processing, and Strength Performance#1103837
• Evaluating Agents Across Runtime Contracts: When Mismatch Costs Efficiency or Quality#1142631
• EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions#305583
• EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions#299988