[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85819-en":3,"doc-seo-85819-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85819,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries","Large language model agents increasingly store reusable procedures outside the model, often called skills that may be code functions, natural-language instructions, SKILL.md packages, workflow graphs, or learned adapters. This taxonomy-driven survey analyzes how skill libraries evolve over time using a 124-paper audit from 2023–2026. It synthesizes lifecycle-managed evidence collection, proposing, verification and admission, retrieval and composition, maintenance with pruning or repair, and governance via provenance and rollback, then summarizes recurring design choices, benchmark gaps, and reporting standards.","arXiv :2607 . 10 1 13v 1 [ cs .AI] 11 Jul 2026  \nDynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries  \nYubo Li  \nCarnegie Mellon University  \n[yubol@andrew. cmu. edu](yubol@andrew. cmu. edu)  \nReviewed on OpenReview: [https://openreview.net/forum?id=cjU3YbcRr8](https://openreview.net/forum?id=cjU3YbcRr8)  \nAbstract  \nLarge language model agents increasingly store reusable procedures outside the model.  \nThese reusable procedures are often called skills: they may be code functions, naturallanguage instructions, SKILL.md packages, workflow graphs, or learned adapters that a future agent can retrieve and invoke. This taxonomy-driven survey asks how such skill libraries change over time. Across a 124-paper 2023–2026 audit set, we synthesize dynamicskill systems as lifecycle-managed, verified, evolving artifact stores: agents collect evidence from interaction, propose skill updates, verify and admit candidates, organize them for retrieval and composition, repair or prune stale entries, and govern sharing through provenance and rollback. We organize the literature around three survey tools. First, a six-sense taxonomy distinguishes the structurally different artifacts called “skills” in current papers.  \nSecond, an eight-stage lifecycle architecture identifies the recurring design decisions behind evidence acquisition, proposal, verification/admission, storage, retrieval/composition, maintenance, distillation/portability, and governance. Third, a lightweight skill-record schema and ten-operator vocabulary provide common terms for comparing library updates without elevating them into a separate method contribution. Using this structure, we synthesize evidence-graded patterns with explicit caveats: admission and repair are repeatedly important, verifier quality materially affects skill-aware RL, flat retrieval can degrade as libraries grow, and current benchmarks still under-report library trajectories, usage–utility gaps, and safety surfaces. We close with concrete reporting standards and open problems for evaluating dynamic skills as changing libraries rather than static prompt or tool collections.  \n1 Introduction  \nLarge language model agents are moving from chat-style assistance into operational workflows. They browse and manipulate web interfaces, write and repair software, operate desktop and computer-use environments, coordinate multi-step research pipelines, interact with embodied environments, and assist domain-specific workflows such as recommendation and medical imaging. Across these settings, the bottleneck is not only whether the model can reason about a single task. It is whether the agent can reuse procedural knowledge across recurring tasks, tools, interfaces, and users instead of re-deriving the same strategy inside every context window.  \nAgent skills were proposed as a practical answer to this reuse problem. In plain terms, a skill is a reusable procedure that an agent can call later. It may be a function, a natural-language instruction, [a SKILL.md](a SKILL.md)[ ](a SKILL.md)directory, a workflow graph, or a learned adapter, but its role is the same: preserve a reusable way of acting so that a future agent can retrieve, compose, and execute it. Early executable libraries such as Voyager and LATM stored code skills; 2025 systems extended skills into web and software agents; 2026 systems expanded the ecosystem into SKILL.md packages, computer-use skills, mobile GUI skills, multimodal skills, benchmarks, registries, and safety audits (Wang et al. , 2023 ; Cai et al. , 2023 ; Zheng et al. , 2025a; Xia et al. , 2025a; Chen et al. , 2026d;b; Jiang et al. , 2026a; Xie et al. , 2026 ; Tao et al. , 2026 ; Fan et al. , 2026) .  \nThe broader skill ecosystem now includes [SKILL.md](SKILL.md) conventions, function-calling schemas, MCP/pluginstyle packaging, and registry-like platforms that support libraries with hundreds or thousands of reusable artifacts (Jiang et al. , 2026b; Zhang et al. , 2025","cbCaio5J9l547OWg","https://ap.wps.com/l/cbCaio5J9l547OWg","pdf",3278757,1,51,"English","en",105,"# Introduction\n## Problem: procedural reuse beyond chat\n## What “skills” mean in this survey\n## System landscape and ecosystem context\n## Survey framework: taxonomy and lifecycle tools","[{\"question\":\"What are “skills” in the context of dynamic agent skill libraries?\",\"answer\":\"Skills are reusable procedures an agent can call later, including code functions, natural-language instructions, SKILL.md packages, workflow graphs, or learned adapters.\"},{\"question\":\"How does the survey explain the lifecycle of skill libraries?\",\"answer\":\"It proposes an eight-stage lifecycle covering evidence acquisition, skill updates proposal, verification/admission, storage, retrieval/composition, maintenance, distillation/portability, and governance.\"},{\"question\":\"Why does the document emphasize verification and repair?\",\"answer\":\"Admission and repair repeatedly matter because verifier quality affects skill-aware reinforcement learning, while stale or growing libraries can degrade retrieval and create safety surfaces.\"}]",1784206445,129,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"dynamic-agent-skills-a-lifecycle-survey-and-taxonomy-of-evolving-skill-libraries","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/dynamic-agent-skills-a-lifecycle-survey-and-taxonomy-of-evolving-skill-libraries/85819/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What are “skills” in the context of dynamic agent skill libraries?","Question",{"text":75,"@type":76},"Skills are reusable procedures an agent can call later, including code functions, natural-language instructions, SKILL.md packages, workflow graphs, or learned adapters.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the survey explain the lifecycle of skill libraries?",{"text":80,"@type":76},"It proposes an eight-stage lifecycle covering evidence acquisition, skill updates proposal, verification/admission, storage, retrieval/composition, maintenance, distillation/portability, and governance.",{"name":82,"@type":73,"acceptedAnswer":83},"Why does the document emphasize verification and repair?",{"text":84,"@type":76},"Admission and repair repeatedly matter because verifier quality affects skill-aware reinforcement learning, while stale or growing libraries can degrade retrieval and create safety surfaces.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]