20 results for “Understanding of AI-generated code”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper investigates the security vulnerabilities of AI-powered code generation systems and proposes a defense framework.
This paper argues for using vibe modeling as a lightweight intermediate abstraction between natural language interaction and code generation in AI-based software engineering, and presents a student su…
Alex Mathai, Shobini Iyer, Aleksandr Nogikh, Petros Maniatis +3 more
This paper introduces TRIM, an algorithm that minimizes redundant edits in AI-generated code, called CodeSlop, by minimizing agent trajectories, reducing CodeSlop by 17.9%-32.9% with negligible perfor…
The paper introduces CodeGolf Bench, a novel multi-language benchmark using code golf to measure LLMs' ability to generate highly concise and efficient code, showing that reasoning models significantl…
The paper introduces CHECKMATE, a novel framework that uses code evolution to automatically generate and optimize algorithms for complex combinatorial problems, outperforming state-of-the-art solvers.
This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…
This paper examines the instruction stacks of five coding agents to understand their composition and evolution.
This paper investigates how developer attributes influence generated software using AI, finding significant differences in interface design, template content, and code structure based on age and gende…
This paper introduces AlgoREval, a benchmark to evaluate the capability of large language models in parametric code retrieval.
This paper analyzes online developer discussions to identify four major security concerns—data leakage, code licensing, adversarial attacks, and insecure suggestions—associated with using generative A…
The paper introduces Spaghetti Architect, a tool that generates controlled code datasets for machine learning models by deliberately adding redundancy, messiness, and difficulty.
Xiaoyong Li, Haolong Li, Dongliang Xu, Haoyu Li +6 more
This paper introduces Code Skill Server (CSS), a large-scale search engine for finding useful code generation skills for a target task.
Zhe Ye, Hantao Lou, Yuechun Sun, Peiyang Song +7 more
The paper introduces Vero, the first benchmark for evaluating joint implementation and proof synthesis at the repository level for AI-generated software.
The paper proposes and evaluates a novel embedding model for bidirectional function association between source code and decompiled/stripped code, significantly outperforming existing models.
This paper investigates code generation for no-resource programming languages using large language models.
This paper identifies the 'Format-Reliability Gap'—where LLMs know about code vulnerabilities but generate insecure code anyway—and proposes a localized, per-vulnerability steering vector fix that sig…
This paper empirically evaluates the security of code generated by seven popular LLMs and finds that all evaluated models generate code containing critical or high-severity vulnerabilities.
The paper proposes an automated, standardized framework to empirically compare the security quality of code generated through human-only, LLM-only, and hybrid collaboration methods.
The authors argue that coding agents can replace traditional human code review in software development.