arXiv AI June 16, 2026 By Rupam Patir, Keyan Guo, Suvadra Barua, Abhijeet Pathak, Dinesh Gudimetla, Jiawei Guo, Hongxin Hu, Haipeng Cai

DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents

Read the original on arXiv AI →

arXiv:2511. 20709v2 Announce Type: replace-cross Abstract: Large language models (LLMs) and LLM-based coding agents are now used to generate code from natural-language specifications, yet ensuring such code is both functionally correct and secure remains a challenge.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language

Sep 15

Toward Secure Code Generation: Bridging Correctness and Security via Task-Adaptive Vulnerability Modeling and Execution-Based Benchmarking

arXiv:2407.02395v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for program synthesis, yet they often generate code that is functionally plausible but ins...

By Jiexin Wang, Liuwen Cao, Xitong Luo, Yang Cao, Zhenghao Li, Yunyi Xiao, Mengchen Zhao, Adam Jatowt, Yi Cai

llms agents benchmarks

arXiv AI

Jun 9

SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios

arXiv:2509. 22097v5 Announce Type: replace-cross Abstract: Large language model-powered code agents are rapidly transforming software engineering, yet the security risks of their generated code have become a critical concern.

By Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo

llms agents benchmarks

arXiv Machine Learning

Jul 1

An Empirical Study of Security Calibration in Large Language Models for Code

arXiv:2606. 31159v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly transforming software development, yet their use in security-critical contexts raises a key question: do models know when their generated code is insecure?

By Mohammed Latif Siddiq, Md. Nafiu Rahman, Joanna C. S. Santos

llms benchmarks

arXiv Machine Learning

Jul 10

Functional and Secure Code Generation with Task Vectors

arXiv:2607. 07881v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for code generation, but they struggle to generate functional code free of security vulnerabilities.

By Felix Wang, Anudeep Das, Mei Nagappan, N. Asokan

llms benchmarks safety

arXiv Computation and Language

3d ago

SecureVibe: Making Vibe Coding More Secure

SecureVibe is a training recipe designed to enhance the security of vibe coding by explicitly targeting planning and testing for code security. It combines supervised fine‑tuning on a security suite with post‑training methods (SECUREVIBE_rl and SECUREVIBE_hg) that use verifiable execution feedback and hint‑based self‑supervision. The approach outperforms baselines on multiple security coding benchmarks, improving security pass@1 by up to 6.9 points on BaxBench and 11.5 points on SusVibes, while also boosting functionality pass@1 on both security and generic coding tasks.

By Danqing Wang, Baolin Peng, Zhepei Wei, Isadora White, Wenlin Yao, Hao Cheng, Qianhui Wu, Minseon Kim, Xingdi Yuan, Lei Li, Jianfeng Gao

agents fine-tuning benchmarks

arXiv AI

Jun 16

SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation

arXiv:2606. 16244v1 Announce Type: cross Abstract: Large language models routinely generate code with exploitable security flaws.

By Xiaoyun Xu, Lichao Wu, Jona te Lintelo, Siyu Zhang, Stjepan Picek

llms rag fine-tuning benchmarks safety data-engineering