Hugging Face Trending Papers June 2, 2026

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

Read the original on Hugging Face Trending Papers →

While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimization at the sequence level.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 3

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

arXiv:2606. 03489v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data.

By Wenqi Chen, Ziyan Zhang, Bing Wang, Lin Liu, Hengheng Zhang, Zhengsu Chen

llms reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jul 21

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

arXiv:2605. 26548v2 Announce Type: replace-cross Abstract: Finding a real vulnerability in complicated systems is a challenging, long-horizon task that demands reasoning across an entire codebase to produce a working proof-of-concept (PoC).

By Hwiwon Lee, Jiawei Liu, Dongjun Kim, Wubing Xia, Ziqi Zhang, Chunqiu Steven Xia, Lingming Zhang

llms agents benchmarks safety

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

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 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 AI

Aug 10

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training

arXiv:2608. 06471v1 Announce Type: cross Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software.

By Amine Lbath, Manan Suri, Aurelien Delaitre, Vadim Okun, Massih-Reza Amini, Ram D. Sriram, Dinesh Manocha

llms agents fine-tuning

Related stories

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

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

Functional and Secure Code Generation with Task Vectors

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

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training