mlsanityData to 14 Oct 2026

Challenges and Future Directions in Agentic Reverse Engineering Systems

arXiv 2604.14317 ↗First posted 15 Apr 2026cs.CR cs.AIcited by 1

On the map: LLM agents and tool use → Agent threats, guardrails and governance

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.

Key facts. Cited by 1 paper 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.

Builds on

27 of 50 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs20 Oct
  2. 2025A Survey on Agentic Security: Applications, Threats and Defenses7 Oct
  3. 2025Training Language Model Agents to Find Vulnerabilities with CTF-Dojo25 Aug
  4. 2025Cyber-Zero: Training Cybersecurity Agents without Runtime29 Jul
  5. 2025SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems30 May
  6. 2025Multi-Agent Systems Execute Arbitrary Malicious Code15 Mar
  7. 2025VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework23 Jan
  8. 2024HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing2 Dec
  9. 2024PentestAgent: Incorporating LLM Agents to Automated Penetration Testing7 Nov
  10. 2024EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities24 Sep

Other references · 17

  1. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  2. 2024LLM4Decompile: Decompiling Binary Code with Large Language Modelscited by 39
  3. 2025LAMD: Context-driven Android Malware Detection and Classification with LLMscited by 18
  4. 2024Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattackscited by 15
  5. 2025CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent Systemcited by 15
  6. 2025IRCopilot: Automated Incident Response with Large Language Modelscited by 13
  7. 2024How Far Have We Gone in Binary Code Understanding Using Large Language Modelscited by 7
  8. 2024Disassembling Obfuscated Executables with LLMcited by 7
  9. 2024WaDec: Decompiling WebAssembly Using Large Language Modelcited by 5
  10. 2025ReCopilot: Reverse Engineering Copilot in Binary Analysiscited by 5
  11. 2025CVE-LLM : Ontology-Assisted Automatic Vulnerability Evaluation Using Large Language Modelscited by 4
  12. 2025BinMetric: A Comprehensive Binary Analysis Benchmark for Large Language Modelscited by 4
5 more
  1. 2025ALT4Decompile: Inferring C-aligned Abstract Loop Tree for LLM-Based Binary Decompilationcited by 4
  2. 2025SoK: Potentials and Challenges of Large Language Models for Reverse Engineeringcited by 3
  3. 2024A Picture is Worth 500 Labels: A Case Study of Demographic Disparities in Local Machine Learning Models for Instagram and TikTokcited by 2
  4. 2022What Your Firmware Tells You Is Not How You Should Emulate It: A Specification-Guided Approach for Firmware Emulation (Extended Version)cited by 1
  5. 2025Binary Diff Summarization using Large Language Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CrackMeBench: Binary Reverse Engineering for Agents
  2. 2026The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark
  3. 2026Reveree: Diagnosing LLM Reverse-Engineering Agents
  4. 2026From Secure Agentic AI to Secure Agentic Web: Challenges, Threats, and Future Directions
  5. 2026Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents
  6. 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
  7. 2026Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
  8. 2026Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation