QRS: A Rule-Synthesizing Neuro-Symbolic Triad for Autonomous Vulnerability Discovery

• URL: http://arxiv.org/abs/2602.09774v1
• Date: Tue, 10 Feb 2026 13:35:24 GMT
• Title: QRS: A Rule-Synthesizing Neuro-Symbolic Triad for Autonomous Vulnerability Discovery
• Abstract summary: We introduce QRS (Query, Review, Sanitize), a neuro-symbolic framework that inverts this paradigm.<n>Rather than filtering results from static rules, QRS employs three autonomous agents that generate CodeQL queries from a structured schema definition and few-shot examples, then validate through semantic reasoning and automated exploit synthesis.<n>In 20 historical CVEs in popular PyPI libraries, QRS 90.6% detection accuracy.
• Score: 3.52359746858894
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Static Application Security Testing (SAST) tools are integral to modern DevSecOps pipelines, yet tools like CodeQL, Semgrep, and SonarQube remain fundamentally constrained: they require expert-crafted queries, generate excessive false positives, and detect only predefined vulnerability patterns. Recent work has explored augmenting SAST with Large Language Models (LLMs), but these approaches typically use LLMs to triage existing tool outputs rather than to reason about vulnerability semantics directly. We introduce QRS (Query, Review, Sanitize), a neuro-symbolic framework that inverts this paradigm. Rather than filtering results from static rules, QRS employs three autonomous agents that generate CodeQL queries from a structured schema definition and few-shot examples, then validate findings through semantic reasoning and automated exploit synthesis. This architecture enables QRS to discover vulnerability classes beyond predefined patterns while substantially reducing false positives. We evaluate QRS on full Python packages rather than isolated snippets. In 20 historical CVEs in popular PyPI libraries, QRS achieves 90.6% detection accuracy. Applied to the 100 most-downloaded PyPI packages, QRS identified 39 medium-to-high-severity vulnerabilities, 5 of which were assigned new CVEs, 5 received documentation updates, while the remaining 29 were independently discovered by concurrent researchers, validating both the severity and discoverability of these findings. QRS accomplishes this with low time overhead and manageable token costs, demonstrating that LLM-driven query synthesis and code review can complement manually curated rule sets and uncover vulnerability patterns that evade existing industry tools.

Related papers

• ARQ: Agentic CodeQL Query Refinement for C/C++ Vulnerability Detection [21.303380348840392]
  We present ARQ, a framework that automatically refines C/C++ CodeQL queries using execution-grounded evidence from synthesized C/C++ programs.<n>Unlike previous query refining methods, ARQ requires no labeled datasets, no commit history, and no vulnerability-specific templates.<n>We show that ARQ-refined queries detect substantially more true positives, by up to 119.8%, with a Precision of at least 98.0% throughout.
  arXiv  Detail & Related papers  (2026-08-21T00:20:55Z)
• EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge [53.44952808455985]
  EvoBrowseComp is an evolving benchmark of 400 English and 400 Chinese complex questions.<n>EvoBrowseComp can be regularly updated to prevent data contamination.<n>It establishes a scalable paradigm for auto-updatable, high-difficulty benchmarking.
  arXiv  Detail & Related papers  (2026-06-11T09:48:32Z)
• Longitudinal Analyses of SAST Tools: A CodeQL Case Study [3.5770847622955064]
  We introduce a novel method to evaluate static application security testing (SAST) tools through longitudinal measurements.<n>We apply our apparatus on 114 versions of CodeQL over time on 3993 CVEs from 1622 repositories to measure key properties of the tool.<n>We find that CodeQL identifies a total of 171 CVEs, and that for 83 of them, a CodeQL version prior to the fix could detect it.
  arXiv  Detail & Related papers  (2026-05-08T15:41:25Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning [58.432996881401415]
  Recent work augments large language models (LLMs) with external tools to enable agentic reasoning.<n>We propose Sponge Tool Attack (STA), which disrupts agentic reasoning solely by rewriting the input prompt.<n>STA generates benign-looking prompt rewrites from the original one with high semantic fidelity.
  arXiv  Detail & Related papers  (2026-01-24T19:36:51Z)
• Multi-Agent Taint Specification Extraction for Vulnerability Detection [49.27772068704498]
  Static Application Security Testing (SAST) tools using taint analysis are widely viewed as providing higher-quality vulnerability detection results.<n>We present SemTaint, a multi-agent system that strategically combines the semantic understanding of Large Language Models (LLMs) with traditional static program analysis.<n>We integrate SemTaint with CodeQL, a state-of-the-art SAST tool, and demonstrate its effectiveness by detecting 106 of 162 vulnerabilities previously undetectable by CodeQL.
  arXiv  Detail & Related papers  (2026-01-15T21:31:51Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• QLCoder: A Query Synthesizer For Static Analysis of Security Vulnerabilities [18.588864089739598]
  QLCoder is an agentic framework that automatically synthesizes queries in CodeQL, a powerful static analysis engine.<n>QLCode embeds an LLM in a synthesis loop with execution feedback, while constraining its reasoning using a custom MCP interface.<n>We evaluate QLCode on 176 existing CVEs across 111 Java projects.
  arXiv  Detail & Related papers  (2025-11-11T17:06:04Z)
• What Do They Fix? LLM-Aided Categorization of Security Patches for Critical Memory Bugs [46.325755802511026]
  We developLM, a dual-method pipeline that integrates two approaches based on a Large Language Model (LLM) and a fine-tuned small language model.<n>LM successfully identified 111 of 5,140 recent Linux kernel patches addressing OOB or UAF vulnerabilities, with 90 true positives confirmed by manual verification.
  arXiv  Detail & Related papers  (2025-09-26T18:06:36Z)
• Large Language Models Versus Static Code Analysis Tools: A Systematic Benchmark for Vulnerability Detection [0.0]
  Three industry-standard rule-based static code-analysis tools (Sonar, CodeQL and Snyk Code) and three state-of-the-art large language models hosted on the GitHub Models platform (GPT-4.1, Mistral Large and DeepSeek V3) were evaluated.<n>Using a curated suite of ten real-world C# projects that embed 63 vulnerabilities, we measure classical accuracy (precision, recall, F-score), analysis latency, granularity and the developer effort required to vet true positives.<n>We recommend a hybrid pipeline: employ language models early in development for broad, context-aware detection and
  arXiv  Detail & Related papers  (2025-08-06T13:48:38Z)
• Decompiling Smart Contracts with a Large Language Model [51.49197239479266]
  Despite Etherscan's 78,047,845 smart contracts deployed on (as of May 26, 2025), a mere 767,520 ( 1%) are open source.<n>This opacity necessitates the automated semantic analysis of on-chain smart contract bytecode.<n>We introduce a pioneering decompilation pipeline that transforms bytecode into human-readable and semantically faithful Solidity code.
  arXiv  Detail & Related papers  (2025-06-24T13:42:59Z)
• Automated Static Vulnerability Detection via a Holistic Neuro-symbolic Approach [17.872674648772616]
  We present MoCQ, a novel neuro-symbolic framework that combines the complementary strengths of Large Language Model (LLM) and classic vulnerability checkers.<n>MoCQ achieves comparable precision and recall compared to expert-developed queries, with significantly less expert time needed.<n>MoCQ also uncovered 46 new vulnerability patterns that experts missed, each representing an overlooked vulnerability class.
  arXiv  Detail & Related papers  (2025-04-22T17:33:53Z)
• KNighter: Transforming Static Analysis with LLM-Synthesized Checkers [20.368621145118468]
  KNighter generates high-precision checkers capable of detecting diverse bug patterns.<n>To date, KNighter-synthesized checkers have discovered 92 new, critical, long-latent bugs in the Linux kernel.
  arXiv  Detail & Related papers  (2025-03-12T02:30:19Z)
• AutoPT: How Far Are We from the End2End Automated Web Penetration Testing? [54.65079443902714]
  We introduce AutoPT, an automated penetration testing agent based on the principle of PSM driven by LLMs. Our results show that AutoPT outperforms the baseline framework ReAct on the GPT-4o mini model.
  arXiv  Detail & Related papers  (2024-11-02T13:24:30Z)
• EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities [46.34031902647788]
  We present EnIGMA, an LM agent for autonomously solving Capture The Flag (CTF) challenges.<n>We introduce new tools and interfaces to improve the agent's ability to find and exploit security vulnerabilities.<n> Empirical analysis on 390 CTF challenges demonstrate that these new tools and interfaces substantially improve our agent's performance.
  arXiv  Detail & Related papers  (2024-09-24T15:06:01Z)

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.