Neo combines LLM-based agents with code search primitives to detect privilege escalation in polyglot microservices, reporting 81% precision and 85% recall while uncovering 24 zero-day vulnerabilities across 25 applications.
Enhancing static analysis for practical bug detection: An llm-integrated approach
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Agentic interpretation uses lattices to track LLM judgments on decomposed program claims during analysis.
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.
SAILOR combines static analysis and LLM-orchestrated synthesis to automatically generate symbolic execution harnesses, discovering 379 previously unknown memory-safety vulnerabilities across 10 large open-source C/C++ projects where the strongest baseline found only 12.
FGDM is a sequential multi-agent system using flow graphs, CoT/ToT prompts, and FAISS retrieval that reports mean Levenshtein distance reductions of 24.33 (Python) and 8.37 (C) with cosine similarities of 0.951 and 0.974 on 100 programs from ten open-source projects.
Augmenting LLMs with bug references, few-shot learning, chain-of-thought, and RAG improves MPI error detection accuracy from 44% to 77% and generalizes across models.
MoCQ combines LLMs with symbolic validation to generate vulnerability patterns for static analysis, matching expert performance on 12 types across four languages and finding 25 new real-world vulnerabilities.
A research roadmap analyzing the current state of search-based software engineering with foundation models, outlining challenges and directions across three integration aspects.
citing papers explorer
-
Detecting Privilege Escalation in Polyglot Microservices via Agentic Program Analysis
Neo combines LLM-based agents with code search primitives to detect privilege escalation in polyglot microservices, reporting 81% precision and 85% recall while uncovering 24 zero-day vulnerabilities across 25 applications.
-
Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis
Agentic interpretation uses lattices to track LLM judgments on decomposed program claims during analysis.
-
NESA: Relational Neuro-Symbolic Static Program Analysis
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.
-
Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery
SAILOR combines static analysis and LLM-orchestrated synthesis to automatically generate symbolic execution harnesses, discovering 379 previously unknown memory-safety vulnerabilities across 10 large open-source C/C++ projects where the strongest baseline found only 12.
-
FGDM: Reasoning Aware Multi-Agentic Framework for Software Bug Detection using Chain of Thought and Tree of Thought Prompting
FGDM is a sequential multi-agent system using flow graphs, CoT/ToT prompts, and FAISS retrieval that reports mean Levenshtein distance reductions of 24.33 (Python) and 8.37 (C) with cosine similarities of 0.951 and 0.974 on 100 programs from ten open-source projects.
-
Improving MPI Error Detection and Repair with Large Language Models and Bug References
Augmenting LLMs with bug references, few-shot learning, chain-of-thought, and RAG improves MPI error detection accuracy from 44% to 77% and generalizes across models.
-
Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns
MoCQ combines LLMs with symbolic validation to generate vulnerability patterns for static analysis, matching expert performance on 12 types across four languages and finding 25 new real-world vulnerabilities.
-
Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap
A research roadmap analyzing the current state of search-based software engineering with foundation models, outlining challenges and directions across three integration aspects.