Research map / Large language models / Agents, code and math
QLCoder: A Query Synthesizer For Static Analysis of Security Vulnerabilities
Claire Wang, Ziyang Li, Saikat Dutta, Mayur Naik
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LSP server (ablation) | QLCoder · Ablation (20 CVEs) | success rate (%): 25% -> 50% | Improved |
| add documentation lookup (ablation) | QLCoder · Ablation (20 CVEs) | success rate (%): 20% -> 50% | Improved |
| add AST cache (ablation) | QLCoder · Ablation (20 CVEs) | success rate (%): 25% -> 50% | Improved |
| add AST cache (ablation) | QLCoder · Ablation (20 CVEs) | recall rate (%): 80% -> 80% | No clear effect |
| add LSP server (ablation) | QLCoder · Ablation (20 CVEs) | recall rate (%): 55% -> 80% | Improved |
| add all QLCoder tools to Claude Code (ablation) | Claude Code · Ablation (20 CVEs) | success rate (%): 10% -> 50% | Improved |
| use QLCoder instead of CodeQL queries | query synthesis · CWE-Bench-Java (shared CVEs: 130) | recall rate (%): 20.0 -> 80.0 | Improved |
| use QLCoder instead of IRIS | query synthesis · CWE-Bench-Java (shared CVEs: 130) | avg precision: 0.031 -> 0.672 | Improved |
| add QLCoder to Claude Code Sonnet 4 | Claude Code · 20 CVEs from 2025 | success rate (%): 10% -> 35% | Improved |
| add QLCoder to Codex GPT-5 Medium | Codex · 20 CVEs from 2025 | success rate (%): 0% -> 20% | Improved |
| add QLCoder to Gemini CLI Gemini 2.5 Pro | Gemini CLI · 20 CVEs from 2025 | success rate (%): 0% -> 0% | No clear effect |
| add QLCoder to Gemini CLI Gemini 2.5 Flash | Gemini CLI · 20 CVEs from 2025 | compilation rate (%): 0% -> 45% | Improved |
Closest papers by meaning
- CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability (ICML 2026 · similarity 0.87)
- IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities (ICLR 2025 · similarity 0.87)
- SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks (NeurIPS 2025 · similarity 0.87)
- MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents (NeurIPS 2026 · similarity 0.86)
- EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities (ICML 2025 · similarity 0.85)
- SecCodePRM: A Process Reward Model for Code Security (ICML 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
