[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85311-en":3,"doc-seo-85311-105":30,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85311,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","FlowArk Boosting Agentic Data-flow Analysis for Android Apps via Context-Aware Knowledge Reuse","Data-flow analysis underpins Android app privacy and security auditing, yet batch agentic workflows using coding agents often repeat expensive source-to-sink reasoning. Different agent instances, context-isolated by design, may inspect identical shared code fragments when taint paths converge on common program logic. FlowArk addresses this bottleneck by distilling completed analysis histories into reusable knowledge candidates, packaging them into matchable entries, and injecting matched knowledge into later agent contexts. On 4,685 tasks across 50 open-source apps, FlowArk preserves analysis quality while cutting end-to-end API cost by 26.83% and completing 36.66% more tasks under a USD 100 budget.","FlowArk: Boosting Agentic Data-flow Analysis for Android Apps via Context-Aware Knowledge Reuse  \nYiming Zhang, Jiangrong Wu, and Yuhong Nan*  \nSun Yat-sen University  \n[zhangym253@mail2.sysu.edu.cn](zhangym253@mail2.sysu.edu.cn) ; [christopppwu@gmail.com](christopppwu@gmail.com) ; [nanyh@mail.sysu.edu.cn](nanyh@mail.sysu.edu.cn)  \narXiv :2607 . 1 1308v 1 [ cs . SE] 13 Jul 2026  \nAbstract—Data-flow analysis is foundational to Android app privacy and security auditing. Recent coding agents can assist with non-trivial source-to-sink data-flow analysis tasks by searching, reading, and reasoning over repository code. However, when these tasks are executed as a batch workload, current agentic analysis setups incur substantial re-analysis cost. Agent instances assigned to different taint sources may inspect shared code fragments, because code reuse in the target app can cause different data-flow paths to converge on shared program logic. Since these agent instances are context-isolated, analysis of these shared code fragments can be repeated within a batch, unnecessarily consuming API budget and limiting scalability.  \nWe propose FlowArk, a knowledge-reuse system that reduces re-analysis cost in batch agentic data-flow analysis by making knowledge from completed analyses available to later agent instances. Specifically, FlowArk distills completed analysis histories into reusable knowledge candidates, packages these candidates into matchable knowledge entries, and injects matched entries into a later agent instance’s context. We implement FlowArk on OpenCode and evaluate it on 4,685 source-to-sink data-flow analysis tasks from 50 open-source Android apps. Compared with standard OpenCode, FlowArk-enabled OpenCode maintains comparable analysis quality while reducing end-to-end API cost by 26.83% . In addition, under a USD 100 budget, FlowArk completes 36.66% more tasks (1,060 vs. 776).  \nI. INTRODUCTION  \nLarge language models and coding agents are being used to support security analysis tasks such as data-flow analysis [1],[2], repository-level security auditing [3], and vulnerability detection [4]–[6] . A common characteristic of these systems is that coding agents can iteratively invoke search and codereading tools within a repository, gradually collect evidence, reason about data-flows, and ultimately produce security analysis results. We refer to source-to-sink data-flow analysis performed in this agent-driven manner as agentic data-flow analysis. This setting is attractive because coding agents can analyze complex cross-file data-flows and reduce the manual effort required to customize taint propagation rules.  \nIn current Android program analysis tasks such as privacy compliance auditing and security vetting, agentic data-flow analysis is often organized as a batch workload. For example, an analyst may define hundreds of untrusted UI input sources and use agents to analyze whether tainted data from each source can reach security-sensitive sink APIs. These data-flow analysis tasks are often assigned to multiple agent instances, or  \n* Corresponding author: Yuhong Nan ([nanyh@mail.sysu.edu.cn](nanyh@mail.sysu.edu.cn)) .  \nFig. 1. The reuse opportunity in batch agentic data-flow analysis. Different agent instances may analyze the same shared code fragment. Reusing prior analysis knowledge can help later agent instances avoid repeated reading and reasoning, reducing unnecessary re-analysis cost across the batch workload.  \nindependent sessions 1 , to reduce task complexity and control the context size. Each agent instance is context-isolated and maintains its own reasoning trace.  \nThis batch analysis setup involves substantial unnecessary re-analysis, which lowers efficiency and increases token consumption. Modern Android apps commonly encapsulate frequently used program logic, such as event dispatch, into shared components for code reuse. Consequently, data-flow analysis tasks that start from different sources can converge on the ","cbCailow2w325xuO","https://ap.wps.com/l/cbCailow2w325xuO","pdf",3086920,4,1,12,"English","en",105,"# Introduction\n## Agentic data-flow analysis as a batch workload\n## Opportunity for reuse across shared code fragments\n## Root cause: lack of effective cross-instance knowledge reuse\n## Limitations of general agent memory systems","[{\"question\":\"What problem does FlowArk target in batch agentic data-flow analysis?\",\"answer\":\"Batch workflows re-analyze shared code fragments across context-isolated agent instances, causing redundant tool calls and reasoning and increasing token/API costs.\"},{\"question\":\"How does FlowArk reuse knowledge between different agent instances?\",\"answer\":\"FlowArk distills completed analysis histories into reusable knowledge candidates, packages them into matchable knowledge entries, and injects matched entries into the later agent instance’s context.\"},{\"question\":\"What results does FlowArk achieve in evaluation?\",\"answer\":\"Compared with standard OpenCode, FlowArk keeps comparable analysis quality while reducing end-to-end API cost by 26.83%, and under a USD 100 budget it completes 36.66% more tasks.\"}]",1784202401,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"flowark-boosting-agentic-data-flow-analysis-for-android-apps-via-context-aware-knowledge-reuse","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/flowark-boosting-agentic-data-flow-analysis-for-android-apps-via-context-aware-knowledge-reuse/85311/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","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 problem does FlowArk target in batch agentic data-flow analysis?","Question",{"text":75,"@type":76},"Batch workflows re-analyze shared code fragments across context-isolated agent instances, causing redundant tool calls and reasoning and increasing token/API costs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does FlowArk reuse knowledge between different agent instances?",{"text":80,"@type":76},"FlowArk distills completed analysis histories into reusable knowledge candidates, packages them into matchable knowledge entries, and injects matched entries into the later agent instance’s context.",{"name":82,"@type":73,"acceptedAnswer":83},"What results does FlowArk achieve in evaluation?",{"text":84,"@type":76},"Compared with standard OpenCode, FlowArk keeps comparable analysis quality while reducing end-to-end API cost by 26.83%, and under a USD 100 budget it completes 36.66% more tasks.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]