ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “Understanding of AI-generated code”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.CRcs.SEEmpiricalRecentJun 9, 2026

Context-Based Adversarial Attacks on AI Code Generators: Vulnerability Analysis and Implications

Walther A. Del Orbe, John D. Hastings, Varghese Vaidyan

This paper investigates the security vulnerabilities of AI-powered code generation systems and proposes a defense framework.

View →
cs.SEEmpiricalRecentJul 30, 2026

The Case for Vibe Modeling: A Missing Step in AI-Based Trustworthy Software Development

Shalini Chakraborty, Michael Mittermaier, Judith Michael

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…

View →
cs.SEcs.AIcs.OSEmpiricalRecentJul 20, 2026

TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization

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…

View →
cs.SEcs.AIRecentMay 28, 2026

CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models

Vedant Padwal

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…

View →
cs.LGcs.AIcs.LORecentMay 29, 2026

Learning to Solve and Optimize by Evolving Code

Veronika Semmelrock, Benedetta Strizzolo, Francesco Zuccato, Gerhard Friedrich +2 more

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.

View →
cs.AIRecentMay 27, 2026

Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning

Mingze Wu, Abhinav Anand, Shweta Verma, Mira Mezini

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…

View →
cs.SEEmpiricalRecentOct 27, 2026

Hidden in Plain Sight: an Empirical Study about The Instruction Stacks of Coding Agents

Felipe de Sant'Anna Paixão, Dhyego Tavares, Eduardo Almeida, Iftekhar Ahmed

This paper examines the instruction stacks of five coding agents to understand their composition and evolution.

View →
cs.SEEmpiricalRecentJul 8, 2026

Biased or Personalized? The Impact of Personal Information on AI-driven Development

Erfan Entezami, Madeline Endres

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…

View →
cs.LGcs.AIcs.CLEmpiricalRecentOct 1, 2026

Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval

Nickil Maveli, Antonio Vergari, Shay B. Cohen

This paper introduces AlgoREval, a benchmark to evaluate the capability of large language models in parametric code retrieval.

View →
cs.SEcs.CRcs.HCApr 9, 2026

Security Concerns in Generative AI Coding Assistants: Insights from Online Discussions on GitHub Copilot

Nicolás E. Díaz Ferreyra, Monika Swetha Gurupathi, Zadia Codabux, Nalin Arachchilage +1 more

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…

View →
cs.LGcs.SEEmpiricalRecentJul 21, 2026

Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator

Yuxiang Ji

The paper introduces Spaghetti Architect, a tool that generates controlled code datasets for machine learning models by deliberately adding redundancy, messiness, and difficulty.

View →
cs.SEcs.IREmpiricalRecentOct 16, 2026

Code Skill Server: A Large-Scale Search Engine for Code Generation Skills

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.

View →
cs.LGcs.AIcs.LOEmpiricalRecentAug 13, 2026

Vero: Can AI Agents Build Formally Verified Software Repositories?

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.

View →
cs.CRcs.LGcs.SEMay 5, 2026

Identifier-Free Code Embedding Models for Scalable Search

Eric Wolos, Michael Doyle

The paper proposes and evaluates a novel embedding model for bidirectional function association between source code and decompiled/stripped code, significantly outperforming existing models.

View →
cs.SEEmpiricalRecentJun 15, 2026

No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages

Alessandro Giagnorio, Alberto Martin-Lopez, Gabriele Bavota

This paper investigates code generation for no-resource programming languages using large language models.

View →
cs.CRcs.LGApr 17, 2026

Surgical Repair of Insecure Code Generation in LLMs

Gustavo Sandoval, Brendan Dolan-Gavitt, Siddharth Garg

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…

View →
cs.SEcs.AIcs.CRRecentMay 21, 2026

Security of LLM-generated Code: A Comparative Analysis

Srivathsan G Morkonda, Mahmoud Selim, Hala Assal

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.

View →
cs.CRcs.SERecentMay 29, 2026

How to Compare the Security of Code Written by Humans to LLM-generated Code

Rebecca Balebako, Jasmine Egl

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.

View →
cs.SEPositionRecentJun 11, 2026

The End of Code Review: Coding Agents Supersede Human Inspection

Martin Monperrus

The authors argue that coding agents can replace traditional human code review in software development.

View →