[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84217-en":3,"doc-seo-84217-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},84217,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","From Atomic Actions to Standard Operating Procedures Iterative Tool Optimization for Self-Evolving LLM Agents","Tool utilization enables Large Language Model (LLM) agents to operate in the real world and tackle complex tasks. Existing agent frameworks rely mainly on static sets of atomic actions, forcing repeated reimplementation of low-level logic and increasing reasoning cost and failure risk. This work proposes self-evolution via reusable Standard Operating Procedures (SOPs) that act as callable higher-order tools. EVOSOP extracts SOPs from execution trajectories and iteratively optimizes the toolset through construction, merging, evaluation, and pruning, improving success while reducing interaction rounds.","From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents  \nHaipeng Ding1,2 , Yuexiang Xie2 , Zhewei Wei1, * , Yaliang Li2,∗ , Bolin Ding2  \n1Renmin University of China, 2Alibaba Group  \narXiv :2607 .0732 1v 1 [ cs .AI] 8 Jul 2026  \nAbstract  \nTool utilization enables Large Language Model (LLM) agents to interact with the real world and resolve complex tasks. However, existing agent frameworks predominantly rely on static toolsets composed of granular atomic actions (e.g., basic file I/O or single-turn search), which forces agents to reinvent low-level logic for every recurring workflow, leading to increased reasoning overhead and failure rates. In this study, we propose that agents can achieve selfevolution by synthesizing these atomic actions into reusable Standard Operating Procedures (SOPs), which function as callable higher-order tools that encapsulate multi-step logic. We further introduce EVOSOP, a framework that empowers agents to extract SOPs from execution trajectories and iteratively optimize the toolset through a systematic lifecycle of construction, merging, evaluation, and pruning. Extensive experiments demonstrate that EVOSOP significantly boosts task success rates while substantially reducing the number of interaction rounds compared to baselines. Our analysis also reveals that iterative tool optimization fosters reliable and efficient tool-use patterns, providing a scalable pathway for the development of selfevolving agents.  \n1 Introduction  \nLarge Language Models (LLMs) (Raffel et al., 2020 ; Touvron et al., 2023 ; Brown et al., 2020) have fundamentally advanced the field of artificial intelligence, demonstrating remarkable capabilities in logical reasoning and general-purpose problem-solving (Chen et al., 2021) . By leveraging external tools, LLM-based agents (Yao et al., 2023 ; Qin et al., 2024 ; Wang et al., 2024) extend these strengths beyond text generation to interact with the real world and solve complex and practical tasks (Mialon et al., 2024) .  \n* Correspondence to: Zhewei Wei ⟨[zhewei@ruc.edu.cn](zhewei@ruc.edu.cn)⟩ and Yaliang Li⟨[yaliang.li@alibaba-inc.com](yaliang.li@alibaba-inc.com)⟩  \nWhile effective tool utilization is critical to the performance of agent systems, existing frameworks predominantly rely on static toolsets of atomic actions, such as basic file I/O, single-turn search, etc. This design forces agents to orchestrate every task through fine-grained sequences of low-level logic, diverging from the hierarchical efficiency seen inhuman problem-solving (Fabiano et al., 2025) . In practice, humans often bypass exhaustive deliberation by employing Standard Operating Procedures (SOPs) that encapsulate multi-step logic into cohesive and high-level routines. Without these abstractions, agents face significantly increased reasoning overhead and a higher risk of cascading errors, particularly in long-term tasks (Pan et al., 2025) .  \nRecent research on tool-augmented agents followed mainly two paths, refining a model’s ability to use specific tools (Qin et al., 2024) and expanding the overall breadth of the available toolset (Lyu et al., 2023) . However, these efforts do not address the fundamental inefficiency of reasoning in long and fragmented sequences of atomic actions. While recent studies (Yuan et al., 2024 ; Liu et al., 2025) enable agents to create new tools dynamically, they typically treat tool addition as a one-time event and lack a mechanism for long-term management. This leads to a bloated toolset where redundant or suboptimal tools accumulate, creating noise and complicating the agent’s decision-making. This implies that a truly self-evolving agent requires more than just the ability to generate tools. It needs a systematic and iterative process to optimize its toolset by pruning ineffective tools, ensuring that evolved SOPs remain efficient and reliable.  \nTo address the aforementioned challenges, we introduce EVOSOP, a fr","cbCaiseyWtWOIeG8","https://ap.wps.com/l/cbCaiseyWtWOIeG8","pdf",458344,1,15,"English","en",105,"# Introduction\n## Problem with static atomic toolsets\n## EVOSOP approach and contributions\n# Preliminaries","[{\"question\":\"Why do static toolsets of atomic actions limit LLM agent performance?\",\"answer\":\"Static atomic toolsets force agents to repeatedly orchestrate fine-grained low-level logic, increasing reasoning overhead and raising the risk of cascading errors in long tasks.\"},{\"question\":\"How does the proposed method enable self-evolving agent capabilities?\",\"answer\":\"It synthesizes frequently used atomic actions into reusable Standard Operating Procedures (SOPs), turning multi-step logic into callable higher-order tools.\"},{\"question\":\"What is EVOSOP and how does it optimize the toolset over time?\",\"answer\":\"EVOSOP runs a continuous optimization loop that extracts SOPs from execution trajectories, then iteratively improves the toolset via construction, merging, evaluation, and pruning to keep tools lean and reliable.\"}]",1784194055,38,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"from-atomic-actions-to-standard-operating-procedures-iterative-tool-optimization-for-self-evolving-llm-agents","",{"@graph":35,"@context":84},[36,53,67],{"@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/from-atomic-actions-to-standard-operating-procedures-iterative-tool-optimization-for-self-evolving-llm-agents/84217/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why do static toolsets of atomic actions limit LLM agent performance?","Question",{"text":74,"@type":75},"Static atomic toolsets force agents to repeatedly orchestrate fine-grained low-level logic, increasing reasoning overhead and raising the risk of cascading errors in long tasks.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the proposed method enable self-evolving agent capabilities?",{"text":79,"@type":75},"It synthesizes frequently used atomic actions into reusable Standard Operating Procedures (SOPs), turning multi-step logic into callable higher-order tools.",{"name":81,"@type":72,"acceptedAnswer":82},"What is EVOSOP and how does it optimize the toolset over time?",{"text":83,"@type":75},"EVOSOP runs a continuous optimization loop that extracts SOPs from execution trajectories, then iteratively improves the toolset via construction, merging, evaluation, and pruning to keep tools lean and reliable.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]