{"total":59,"rows":[{"id":"2603.00729","title":"Qwen3-Coder-Next Technical Report","created":"2026-02-28","cited_by_count":71,"area":"agents"},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2506.05692","title":"SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code","created":"2025-06-06","cited_by_count":19,"area":null},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2504.21205","title":"SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories","created":"2025-04-29","cited_by_count":14,"area":"agents"},{"id":"2508.18106","title":"A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code","created":"2025-08-25","cited_by_count":14,"area":null},{"id":"2509.22097","title":"SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios","created":"2025-09-26","cited_by_count":13,"area":"agents"},{"id":"2503.15554","title":"Rethinking the Evaluation of Secure Code Generation","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2506.00419","title":"Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences","created":"2025-05-31","cited_by_count":10,"area":"alignment"},{"id":"2502.03233","title":"Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation","created":"2025-02-05","cited_by_count":9,"area":"rag"},{"id":"2510.02609","title":"RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents","created":"2025-10-02","cited_by_count":9,"area":"agents"},{"id":"2606.04460","title":"CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities","created":"2026-06-03","cited_by_count":8,"area":null},{"id":"2510.18204","title":"RESCUE: Retrieval Augmented Secure Code Generation","created":"2025-10-21","cited_by_count":7,"area":"rag"},{"id":"2602.07422","title":"Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model","created":"2026-02-07","cited_by_count":6,"area":"alignment"},{"id":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"id":"2601.13864","title":"HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation","created":"2026-01-20","cited_by_count":5,"area":null},{"id":"2503.14281","title":"XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants","created":"2025-03-18","cited_by_count":4,"area":null},{"id":"2504.15284","title":"EditLord: Learning Code Transformation Rules for Code Editing","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2506.07313","title":"SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows","created":"2025-06-08","cited_by_count":4,"area":"agents"},{"id":"2509.16749","title":"Evaluating LLM Generated Detection Rules in Cybersecurity","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2510.13859","title":"Benchmarking Correctness and Security in Multi-Turn Code Generation","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2605.30777","title":"What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2510.07189","title":"Secure-Instruct: An Automated Pipeline for Synthesizing Instruction-Tuning Datasets Using LLMs for Secure Code Generation","created":"2025-10-08","cited_by_count":2,"area":"synth"},{"id":"2602.23407","title":"Learning to Generate Secure Code via Token-Level Rewards","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2605.24300","title":"Enhancing Reliability in LLM-Based Secure Code Generation","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2605.29737","title":"Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2505.20505","title":"Large Language Models for IT Automation Tasks: Are We There Yet?","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2510.18131","title":"BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2511.03898","title":"Secure Code Generation at Scale with Reflexion","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2511.20709","title":"DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents","created":"2025-11-24","cited_by_count":1,"area":"agents"},{"id":"2602.04894","title":"Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.15485","title":"SecCodeBench-V2 Technical Report","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.10072","title":"Why LLMs Fail: A Failure Analysis and Partial Success Measurement for Automated Security Patch Generation","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2603.10969","title":"TOSSS: a CVE-based Software Security Benchmark for Large Language Models","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.03587","title":"SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization","created":"2026-04-04","cited_by_count":1,"area":"lr"},{"id":"2605.16829","title":"Constrained Code Generation with Discrete Diffusion","created":"2026-05-16","cited_by_count":1,"area":"diffusion"},{"id":"2606.13757","title":"SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2607.27409","title":"SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2609.10548","title":"When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2511.04538","title":"From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2512.04442","title":"TaskEval: Synthesised Evaluation for Foundation-Model Tasks","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2603.01494","title":"Inference-Time Safety For Code LLMs Via Retrieval-Augmented Revision","created":"2026-03-02","cited_by_count":0,"area":"rag"},{"id":"2603.11212","title":"Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.17763","title":"A Quasi-Experimental Developer Study of Security Training in LLM-Assisted Web Application Development","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.16244","title":"Activating Latent Security Knowledge through LLM-Guided Risk Analysis for Secure Code Generation","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.25195","title":"SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward","created":"2026-06-23","cited_by_count":0,"area":"agents"},{"id":"2608.00739","title":"EduPluginBench: Executable Assurance for AI-Generated Educational Plugins","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.05659","title":"Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks","created":"2026-08-06","cited_by_count":0,"area":"safety"},{"id":"2608.15092","title":"WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.25457","title":"MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2609.12708","title":"What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.17817","title":"Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.23980","title":"MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.38606","title":"SecureVibe: Making Vibe Coding More Secure","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.14766","title":"Last Secure Code Benchmark: Is the Code You Vibe Secure?","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.15150","title":"Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.15482","title":"Security in LLM-Assisted Coding: A Systematic Literature Review","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}