# Challenges and Future Directions in Agentic Reverse Engineering Systems

arXiv: https://arxiv.org/abs/2604.14317 · HTML: https://mlsanity.com/paper/2604.14317/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 27 of 27)

- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Multi-Agent Systems Execute Arbitrary Malicious Code](https://mlsanity.com/paper/2503.12188/) (2025)
- [EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities](https://mlsanity.com/paper/2409.16165/) (2024)
- [PentestAgent: Incorporating LLM Agents to Automated Penetration Testing](https://mlsanity.com/paper/2411.05185/) (2024)
- [LLM4Decompile: Decompiling Binary Code with Large Language Models](https://mlsanity.com/paper/2403.05286/) (2024)
- [HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing](https://mlsanity.com/paper/2412.01778/) (2024)
- [VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2501.13411/) (2025)
- [SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems](https://mlsanity.com/paper/2505.24201/) (2025)
- [Cyber-Zero: Training Cybersecurity Agents without Runtime](https://mlsanity.com/paper/2508.00910/) (2025)
- [A Survey on Agentic Security: Applications, Threats and Defenses](https://mlsanity.com/paper/2510.06445/) (2025)
- [LAMD: Context-driven Android Malware Detection and Classification with LLMs](https://mlsanity.com/paper/2502.13055/) (2025)
- [Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks](https://mlsanity.com/paper/2410.20911/) (2024)
- [CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System](https://mlsanity.com/paper/2505.04254/) (2025)
- [Training Language Model Agents to Find Vulnerabilities with CTF-Dojo](https://mlsanity.com/paper/2508.18370/) (2025)
- [IRCopilot: Automated Incident Response with Large Language Models](https://mlsanity.com/paper/2505.20945/) (2025)
- [How Far Have We Gone in Binary Code Understanding Using Large Language Models](https://mlsanity.com/paper/2404.09836/) (2024)
- [Disassembling Obfuscated Executables with LLM](https://mlsanity.com/paper/2407.08924/) (2024)
- [WaDec: Decompiling WebAssembly Using Large Language Model](https://mlsanity.com/paper/2406.11346/) (2024)
- [ReCopilot: Reverse Engineering Copilot in Binary Analysis](https://mlsanity.com/paper/2505.16366/) (2025)
- [CVE-LLM : Ontology-Assisted Automatic Vulnerability Evaluation Using Large Language Models](https://mlsanity.com/paper/2502.15932/) (2025)
- [BinMetric: A Comprehensive Binary Analysis Benchmark for Large Language Models](https://mlsanity.com/paper/2505.07360/) (2025)
- [ALT4Decompile: Inferring C-aligned Abstract Loop Tree for LLM-Based Binary Decompilation](https://mlsanity.com/paper/2509.14646/) (2025)
- [SoK: Potentials and Challenges of Large Language Models for Reverse Engineering](https://mlsanity.com/paper/2509.21821/) (2025)
- [A Picture is Worth 500 Labels: A Case Study of Demographic Disparities in Local Machine Learning Models for Instagram and TikTok](https://mlsanity.com/paper/2403.19717/) (2024)
- [What Your Firmware Tells You Is Not How You Should Emulate It: A Specification-Guided Approach for Firmware Emulation (Extended Version)](https://mlsanity.com/paper/2208.07833/) (2022)
- [Binary Diff Summarization using Large Language Models](https://mlsanity.com/paper/2509.23970/) (2025)
- [Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs](https://mlsanity.com/paper/2510.17521/) (2025)

## Built on by (most cited first, 1 of 1)

- [Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering](https://mlsanity.com/paper/2610.14960/) (2026)

## Abstract (arXiv)

Agentic systems built on large language models (LLMs) are increasingly being used for complex security tasks, including binary reverse engineering (RE). Despite recent growth in popularity and capability, these systems continue to face limitations in realistic settings. Cutting-edge systems still fail in complex RE scenarios that involve obfuscation, timing, and unique architecture. In this work, we examine how agentic systems perform reverse engineering tasks with static, dynamic, and hybrid agents. Through an analysis of existing agentic tool usage, we identify several limitations, including token constraints, struggles with obfuscation, and a lack of program guardrails. From these findings, we outline current challenges and position future directions for system designers to overcome from a security perspective.