{"total":75,"rows":[{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95,"area":"agents"},{"id":"2605.11086","title":"ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?","created":"2026-05-11","cited_by_count":29,"area":"agents"},{"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":"2510.06445","title":"A Survey on Agentic Security: Applications, Threats and Defenses","created":"2025-10-07","cited_by_count":20,"area":"agents"},{"id":"2605.12015","title":"SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces","created":"2026-05-12","cited_by_count":19,"area":"agents"},{"id":"2605.14153","title":"ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents","created":"2026-05-13","cited_by_count":19,"area":"agents"},{"id":"2604.02947","title":"AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents","created":"2026-04-03","cited_by_count":18,"area":"agents"},{"id":"2508.18370","title":"Training Language Model Agents to Find Vulnerabilities with CTF-Dojo","created":"2025-08-25","cited_by_count":15,"area":"agents"},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"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":"2512.23128","title":"It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents","created":"2025-12-29","cited_by_count":10,"area":"agents"},{"id":"2602.03012","title":"CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability","created":"2026-02-03","cited_by_count":9,"area":"agents"},{"id":"2605.26548","title":"SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?","created":"2026-05-26","cited_by_count":9,"area":null},{"id":"2602.03100","title":"Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment","created":"2026-02-03","cited_by_count":8,"area":"agents"},{"id":"2604.05013","title":"Scaling Coding Agents via Atomic Skills","created":"2026-04-06","cited_by_count":8,"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":"2607.01793","title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification","created":"2026-07-02","cited_by_count":7,"area":"agents"},{"id":"2510.26852","title":"CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments","created":"2025-10-30","cited_by_count":5,"area":"agents"},{"id":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"id":"2605.10779","title":"LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments","created":"2026-05-11","cited_by_count":5,"area":"agents"},{"id":"2510.14700","title":"LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?","created":"2025-10-16","cited_by_count":4,"area":"agents"},{"id":"2602.14012","title":"From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection","created":"2026-02-15","cited_by_count":4,"area":"alignment"},{"id":"2602.17547","title":"KLong: Training LLM Agent for Extremely Long-horizon Tasks","created":"2026-02-19","cited_by_count":4,"area":"agents"},{"id":"2603.02297","title":"ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense","created":"2026-03-02","cited_by_count":4,"area":"agents"},{"id":"2604.11950","title":"AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection","created":"2026-04-13","cited_by_count":4,"area":"agents"},{"id":"2510.17862","title":"When \"Correct\" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?","created":"2025-10-15","cited_by_count":3,"area":"agents"},{"id":"2602.13574","title":"Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation","created":"2026-02-14","cited_by_count":3,"area":"lr"},{"id":"2605.03952","title":"MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents","created":"2026-05-05","cited_by_count":3,"area":"agents"},{"id":"2606.00579","title":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers","created":"2026-05-30","cited_by_count":3,"area":"mllm"},{"id":"2601.13933","title":"VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution","created":"2026-01-20","cited_by_count":2,"area":"agents"},{"id":"2605.10597","title":"CrackMeBench: Binary Reverse Engineering for Agents","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.27489","title":"HARP: Measuring Harm Amplification in Multi-Agent LLM Systems","created":"2026-05-26","cited_by_count":2,"area":"agents"},{"id":"2605.30105","title":"EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2608.03392","title":"Self-Evolving Coding Agents","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2609.04075","title":"PatchBench: Evaluating AI Agents for Vulnerability Patching","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2610.07557","title":"CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?","created":"2026-10-06","cited_by_count":2,"area":null},{"id":"2602.02595","title":"To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack","created":"2026-02-01","cited_by_count":1,"area":"safety"},{"id":"2603.11082","title":"Quality-Driven Agentic Reasoning for LLM-Assisted Software Design: Questions-of-Thoughts (QoT) as a Time-Series Self-QA Chain","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2603.13384","title":"VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection","created":"2026-03-11","cited_by_count":1,"area":"agents"},{"id":"2604.06367","title":"WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks","created":"2026-04-07","cited_by_count":1,"area":"agents"},{"id":"2605.15097","title":"Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2605.15132","title":"APWA: A Distributed Architecture for Parallelizable Agentic Workflows","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2605.20351","title":"Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2606.22263","title":"Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases","created":"2026-06-20","cited_by_count":1,"area":"agents"},{"id":"2607.04729","title":"RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2607.24780","title":"LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2607.25379","title":"Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response","created":"2026-07-28","cited_by_count":1,"area":"agents"},{"id":"2607.29422","title":"AgenticRepair: Multi-Faceted Program Context Engineering for Agentic Vulnerability Repair","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2608.11469","title":"The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark","created":"2026-08-11","cited_by_count":1,"area":"agents"},{"id":"2609.08040","title":"VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2609.33763","title":"SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2601.21070","title":"Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2604.01637","title":"Seclens: Role-specific Evaluation of LLM's for security vulnerablity detection","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.05000","title":"Agentic Vulnerability Reasoning on COTS Binaries","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2605.19722","title":"Measuring Safety Alignment Effects in Autonomous Security Agents","created":"2026-05-19","cited_by_count":0,"area":"agents"},{"id":"2605.21615","title":"ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage","created":"2026-05-20","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":"2607.16660","title":"From Adoption to Deployment: A Qualitative Study on AI Integration in Software Development Practice","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.27030","title":"HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.06471","title":"CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.09567","title":"From Runnable to Verifiable: An Independent Reproducibility Study of LLM/Agent-Driven Vulnerability Validation Artifacts","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.21107","title":"Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.25158","title":"FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.15939","title":"Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.23377","title":"One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2609.23980","title":"MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.25591","title":"Evaluating Coding Agents on Kernel Exploit Generation","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.32424","title":"CyberClear: A Benchmark for LLM Agent Systems on APT Attack Chain Provenance","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.36635","title":"WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.03014","title":"Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.03361","title":"Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.06584","title":"Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.14350","title":"Natural Code Transformation Confuses Agents in Vulnerability Analysis","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.17020","title":"CWE-bench: Refocusing Agentic Security from Exploitation to Defense","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}