DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection

arXiv:2607.13439 · cs.CR, cs.SE · Submitted 2026-07-15 · Read on arXiv

Mingyang Sun, Guozhu Meng

cs.CR, cs.SE

Submitted: 2026-07-15

Comments: Accepted for presentation at Internetware 2026. 12 pages, 4 figures, and 5 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 18× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Decoupled Reasoning and Exploration Agents — 8× in this paper
• Accuracy — 7× in this paper · explained in 1 episode
• Lucky Hit Rate — 6× in this paper
• LLM-as-a-Judge — 5× in this paper · explained in 3 episodes
• RAG — 5× in this paper · explained in 3 episodes
• Benchmarking — 3× in this paper · explained in 4 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• Security and Privacy — 3× in this paper
• Trace — 3× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Decoupling — 2× in this paper · explained in 2 episodes
• False Positive Rate — 2× in this paper
• Grounding — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Reasoning Accuracy — 2× in this paper
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Structured Reasoning — 2× in this paper · explained in 3 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Analyzer — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Common Weakness Enumeration — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• SecVulEval: Benchmarking LLMs for Real-World C/C++ Vulnerability Detection
• AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection
• Vulnerability Detection with Code Language Models: How Far Are We?
• Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG
• Improving Factuality and Reasoning in Language Models through Multiagent Debate
• To Err is Machine: Vulnerability Detection Challenges LLM Reasoning
• Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection & Repair in the IDE
• LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning
• ReposVul: A Repository-Level High-Quality Vulnerability Dataset
• VulEval: Towards Repository-Level Evaluation of Software Vulnerability Detection
• R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
• MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution
• Agentless: Demystifying LLM-based Software Engineering Agents
• Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering
• Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• Context-Enhanced Vulnerability Detection Based on Large Language Model
• Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models
• Mono: Is Your "Clean" Vulnerability Dataset Really Solvable? Exposing and Trapping Undecidable Patches and Beyond
• Outside the Comfort Zone: Analysing LLM Capabilities in Software Vulnerability Detection

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs