AI 中文总结
研究安卓应用数据流分析中批量任务重复分析成本高的问题，提出FlowArk系统，通过提炼、打包和注入知识条目降低成本，实验表明其在保持分析质量的同时，能降低API成本并增加任务完成量。
AI 中文摘要
数据流分析是安卓应用隐私和安全审计的基础。近期的编码代理可通过在代码库中搜索、读取和推理来协助非平凡的源到汇数据流分析任务。但批量执行这些任务时，当前的智能分析设置会产生大量重复分析成本。因为目标应用中的代码重用会使不同数据流路径汇聚到共享程序逻辑，不同代理实例可能检查共享代码片段，而它们上下文隔离，导致共享代码片段分析重复。我们提出FlowArk，通过让后续代理实例可用已完成分析的知识来降低批量智能数据流分析中的重复分析成本。具体而言，FlowArk将已完成的分析历史提炼为可重用知识候选，打包成可匹配的知识条目，并注入后续代理实例的上下文。我们在OpenCode上实现FlowArk，并在来自50个开源安卓应用的4685个源到汇数据流分析任务上进行评估。与标准OpenCode相比，启用FlowArk的OpenCode在保持可比分析质量的同时，将端到端API成本降低了26.83%。此外，在100美元预算下，FlowArk能多完成36.66%的任务（1060个对776个）。
英文摘要
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. We 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).
Comments12 pages, 9 figures, 6 tables
