# FlowArk: Boosting Agentic Data-flow Analysis for Android Apps via Context-Aware Knowledge Reuse

arXiv: https://arxiv.org/abs/2607.11308 · HTML: https://mlsanity.com/paper/2607.11308/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 23 of 23)

- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [Repoformer: Selective Retrieval for Repository-Level Code Completion](https://mlsanity.com/paper/2403.10059/) (2024)
- [RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing](https://mlsanity.com/paper/2501.18160/) (2025)
- [Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories](https://mlsanity.com/paper/2503.03586/) (2025)
- [KNighter: Transforming Static Analysis with LLM-Synthesized Checkers](https://mlsanity.com/paper/2503.09002/) (2025)
- [LLMDFA: Analyzing Dataflow in Code with Large Language Models](https://mlsanity.com/paper/2402.10754/) (2024)
- [Improving Code Localization with Repository Memory](https://mlsanity.com/paper/2510.01003/) (2025)
- [Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask](https://mlsanity.com/paper/2504.13474/) (2025)
- [ReCode: Unify Plan and Action for Universal Granularity Control](https://mlsanity.com/paper/2510.23564/) (2025)
- [Harnessing the Power of LLM to Support Binary Taint Analysis](https://mlsanity.com/paper/2310.08275/) (2023)
- [The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget](https://mlsanity.com/paper/2508.13666/) (2025)
- [MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences](https://mlsanity.com/paper/2601.06789/) (2026)
- [QLCoder: A Query Synthesizer For Static Analysis of Security Vulnerabilities](https://mlsanity.com/paper/2511.08462/) (2025)
- [VERCATION: Precise Vulnerable Open-source Software Version Identification based on Static Analysis and LLM](https://mlsanity.com/paper/2408.07321/) (2024)
- [Combining Large Language Models with Static Analyzers for Code Review Generation](https://mlsanity.com/paper/2502.06633/) (2025)
- [The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs](https://mlsanity.com/paper/2504.11711/) (2025)
- [Your Code Agent Can Grow Alongside You with Structured Memory](https://mlsanity.com/paper/2603.13258/) (2026)
- [A Comprehensive Evaluation of Android ICC Resolution Techniques](https://mlsanity.com/paper/2111.05649/) (2021)
- [Multi-Agent Taint Specification Extraction for Vulnerability Detection](https://mlsanity.com/paper/2601.10865/) (2026)
- [LLM-based Vulnerability Detection at Project Scale: An Empirical Study](https://mlsanity.com/paper/2601.19239/) (2026)
- [vEcho: A Paradigm Shift from Vulnerability Verification to Proactive Discovery with Large Language Models](https://mlsanity.com/paper/2603.01154/) (2026)

## Abstract (arXiv)

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).