Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering

arXiv:2610.14960 · cs.SE, cs.AI · Submitted 2026-10-10 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-10-10

Updated: 2026-10-10

Code: https://github.com/horsicq/detect-it-easy

Terminology

• AI Agents — 1× in this paper · explained in 2 episodes

Sources

• ReCopilot: Reverse Engineering Copilot in Binary Analysis
• Potential and Challenges of Large Language Models for Reverse Engineering
• MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
• Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries
• Pop Quiz! Can a Large Language Model Help With Reverse Engineering?
• Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering
• Challenges and Future Directions in Agentic Reverse Engineering Systems
• Deconstructing Obfuscation: A four-dimensional framework for evaluating Large Language Models assembly code deobfuscation capabilities
• Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties