DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection
- URL: http://arxiv.org/abs/2607.13439v1
- Date: Wed, 15 Jul 2026 04:49:05 GMT
- Title: DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection
- Abstract summary: We present DREA, a hypothesis-driven framework for repository-level vulnerability detection.<n>Goal-directed context acquisition is the primary source of detection improvement in this design.<n>To support evaluation, we construct RepoPairBench, a repository-grounded benchmark of validated Python vulnerability-fix pairs from real-world projects.
- Score: 16.007199928732614
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models (LLMs) are increasingly applied to vulnerability detection due to their strong code comprehension capabilities, but most existing approaches rely on isolated functions or context extracted by fixed program-analysis rules. These methods cannot adaptively explore repository-level dependencies to gather sufficient context when vulnerabilities span multiple functions or files, compromising detection reliability. We present DREA (Decoupled Reasoning and Exploration Agents), a hypothesis-driven framework for repository-level vulnerability detection. DREA decouples reasoning from exploration through two collaborating agents: a planning agent backed by an advanced LLM that forms vulnerability hypotheses and directs the investigation, and an explorer agent powered by a lightweight model that retrieves repository-level context on demand. Goal-directed context acquisition is the primary source of detection improvement in this design, while offloading token-heavy exploration to the local model keeps inference economically tractable. To support evaluation, we construct RepoPairBench, a repository-grounded benchmark of validated Python vulnerability-fix pairs from real-world projects. Beyond binary detection accuracy, we introduce a reasoning correctness evaluation to assess whether a model's rationale matches the documented vulnerability mechanism. Across three LLMs, DREA improves Pair-Correctness from 19-26% to 30-42% while offloading over 93% of tokens to the explorer, reducing estimated billable API cost by a factor of 16-48. Reasoning correctness analysis further reveals that 26-55% of true positives, for both DREA and the function-only baseline, are correct predictions supported by flawed rationales, identifying security reasoning quality as a shared bottleneck for current LLMs.
Related papers
- From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents [75.69180947909148]
We propose a trajectory-level UQ framework for large language model (LLM) agents.<n>RuPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges.<n>We evaluate RUPA on representative agent benchmarks, including $$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families.
arXiv Detail & Related papers (2026-08-17T01:40:14Z) - RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations [51.43574078961796]
We introduce RepoMirage, a two-stage evaluation suite built on SWE-Bench Verified.<n>RepoMirage-Perturb applies three types of semantics-preserving repository-level perturbations, revealing a clear performance drop when correct solving requires broader context access.<n>We propose RepoAnchor, a structure-first prototype workflow that separates repository exploration from downstream problem solving.
arXiv Detail & Related papers (2026-05-25T06:26:43Z) - BLAgent: Agentic RAG for File-Level Bug Localization [2.2917707112773593]
BLAgent is a novel agentic RAG framework for file-level bug localization.<n> BLAgent attains over 78% Top-1 accuracy with open-source models.<n> BLAgent improves end-to-end repair success by over 20%.
arXiv Detail & Related papers (2026-05-18T07:20:13Z) - Veritas: A Semantically Grounded Agentic Framework for Memory Corruption Vulnerability Detection in Binaries [14.42294978688412]
We present Veritas, a semantically grounded framework for binary memory corruption vulnerability detection.<n>Veritas combines a static slicer over RetDec-lifted LLVM IR, a dual-view LLM detector, and a multi-agent validator.<n>We implement Veritas as a modular pipeline and evaluate it on a curated benchmark of real-world binary vulnerability cases.
arXiv Detail & Related papers (2026-05-14T17:16:11Z) - From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization [14.474705451897691]
We present T2L-Agent, a project-level, end-to-end framework that plans its own analysis and narrows scope from modules to exact vulnerable lines.<n>We benchmark T2L-ARVO, a diverse, expert-verified 50-case benchmark spanning five crash families and real-world projects.<n>On T2L-ARVO, T2L-Agent achieves up to 58.0% detection and 54.8% line-level localization, substantially outperforming baselines.
arXiv Detail & Related papers (2025-09-30T22:27:18Z) - Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
arXiv Detail & Related papers (2025-09-25T14:05:55Z) - VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
arXiv Detail & Related papers (2025-09-15T02:25:38Z) - TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data [62.22804234013273]
We propose a simple failure detection framework to unify and facilitate classification with rejection under both covariate and semantic shifts.<n>Our key insight is that by separating and consolidating failure-specific reliability knowledge with low-rank adapters, we can enhance the failure detection ability effectively and flexibly.
arXiv Detail & Related papers (2025-04-20T09:20:55Z) - Lie Detector: Unified Backdoor Detection via Cross-Examination Framework [68.45399098884364]
We propose a unified backdoor detection framework in the semi-honest setting.<n>Our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines.<n> Notably, it is the first to effectively detect backdoors in multimodal large language models.
arXiv Detail & Related papers (2025-03-21T06:12:06Z) - Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories [8.583591493627276]
We introduce JitVul, a vulnerability detection benchmark linking each function to its vulnerability-introducing and fixing commits.<n>We show that ReAct Agents, leveraging thought-action-observation and interprocedural context, perform better than LLMs in distinguishing vulnerable from benign code.
arXiv Detail & Related papers (2025-03-05T15:22:24Z) - TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation [31.231916859341865]
TrustRAG is a framework that systematically filters malicious and irrelevant content before it is retrieved for generation.<n>TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance.
arXiv Detail & Related papers (2025-01-01T15:57:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.