AI-generated security pull requests frequently contain a small set of recurring weaknesses, with many flawed ones merged and rejections driven by process factors rather than technical issues.
Available: https://arxiv.org/abs/2506.11022
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
LLMs achieve only 0-60% success when asked to contribute code to sizable open-source projects, often failing basic checks or simply repeating training data.
LLM integration in software engineering builds epistemological debt that erodes mental models and homogenizes code via recursive training, risking systemic fragility as illustrated by 2026 Amazon outages.
Human-Certified Module Repositories (HCMRs) are proposed as a new architectural model blending human oversight with automated analysis to certify reusable software modules for safe assembly by humans and AI agents.
citing papers explorer
-
Insights into Security-Related AI-Generated Pull Requests
AI-generated security pull requests frequently contain a small set of recurring weaknesses, with many flawed ones merged and rejections driven by process factors rather than technical issues.
-
Security Considerations for Multi-agent Systems
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
-
Can LLMs be Effective Code Contributors? A Study on Open-source Projects
LLMs achieve only 0-60% success when asked to contribute code to sizable open-source projects, often failing basic checks or simply repeating training data.
-
Cognitive Atrophy and Systemic Collapse in AI-Dependent Software Engineering
LLM integration in software engineering builds epistemological debt that erodes mental models and homogenizes code via recursive training, risking systemic fragility as illustrated by 2026 Amazon outages.
-
Human-Certified Module Repositories for the AI Age
Human-Certified Module Repositories (HCMRs) are proposed as a new architectural model blending human oversight with automated analysis to certify reusable software modules for safe assembly by humans and AI agents.