{"total":90,"rows":[{"id":"2503.22738","title":"ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning","created":"2025-03-26","cited_by_count":151,"area":"lr"},{"id":"2503.09648","title":"A Survey on Trustworthy LLM Agents: Threats and Countermeasures","created":"2025-03-12","cited_by_count":96,"area":"agents"},{"id":"2503.17332","title":"CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities","created":"2025-03-21","cited_by_count":96,"area":"agents"},{"id":"2503.23350","title":"A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models","created":"2025-03-30","cited_by_count":87,"area":"agents"},{"id":"2507.06134","title":"OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety","created":"2025-07-08","cited_by_count":75,"area":"agents"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2505.19443","title":"Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI","created":"2025-05-26","cited_by_count":42,"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":"2602.16901","title":"AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks","created":"2026-02-18","cited_by_count":39,"area":"agents"},{"id":"2505.24019","title":"LLM Agents Should Employ Security Principles","created":"2025-05-29","cited_by_count":29,"area":"agents"},{"id":"2511.05269","title":"TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems","created":"2025-11-07","cited_by_count":26,"area":"agents"},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2509.21011","title":"Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools","created":"2025-09-25","cited_by_count":18,"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":"2512.02445","title":"When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents","created":"2025-12-02","cited_by_count":15,"area":"agents"},{"id":"2505.11063","title":"Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction","created":"2025-05-16","cited_by_count":14,"area":"lr"},{"id":"2602.02613","title":"Exploring Silicon-Based Societies: An Early Study of the Moltbook Agent Community","created":"2026-02-02","cited_by_count":13,"area":"agents"},{"id":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2509.01211","title":"Web Fraud Attacks Against LLM-Driven Multi-Agent Systems","created":"2025-09-01","cited_by_count":10,"area":"agents"},{"id":"2508.11425","title":"Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments","created":"2025-08-15","cited_by_count":9,"area":"agents"},{"id":"2508.14031","title":"Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation","created":"2025-08-19","cited_by_count":9,"area":"agents"},{"id":"2511.18467","title":"Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems","created":"2025-11-23","cited_by_count":9,"area":"agents"},{"id":"2507.09329","title":"When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agents","created":"2025-07-12","cited_by_count":8,"area":"agents"},{"id":"2509.25624","title":"STAC: When Innocent Tools Form Dangerous Chains for LLM Agents","created":"2025-09-30","cited_by_count":8,"area":"agents"},{"id":"2511.10949","title":"Exposing Weak Links in Multi-Agent Systems under Adversarial Prompting","created":"2025-11-14","cited_by_count":8,"area":"agents"},{"id":"2602.11749","title":"AIR: Improving Agent Safety through Incident Response","created":"2026-02-12","cited_by_count":8,"area":"agents"},{"id":"2603.25111","title":"SEVerA: Verified Synthesis of Self-Evolving Agents","created":"2026-03-26","cited_by_count":8,"area":"agents"},{"id":"2507.19598","title":"MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2510.01359","title":"Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks","created":"2025-10-01","cited_by_count":7,"area":"agents"},{"id":"2510.11688","title":"PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities","created":"2025-10-13","cited_by_count":7,"area":null},{"id":"2605.03228","title":"Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory","created":"2026-05-04","cited_by_count":7,"area":"agents"},{"id":"2504.07461","title":"Achilles Heel of Distributed Multi-Agent Systems","created":"2025-04-10","cited_by_count":6,"area":"agents"},{"id":"2505.17455","title":"Towards Evaluating Proactive Risk Awareness of Multimodal Language Models","created":"2025-05-23","cited_by_count":6,"area":"mllm"},{"id":"2509.24240","title":"Takedown: How It's Done in Modern Coding Agent Exploits","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2606.01317","title":"SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces","created":"2026-05-31","cited_by_count":6,"area":"agents"},{"id":"2606.05391","title":"Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2503.17953","title":"Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts","created":"2025-03-23","cited_by_count":5,"area":"safety"},{"id":"2507.00979","title":"Enhancing LLM Agent Safety via Causal Influence Prompting","created":"2025-07-01","cited_by_count":5,"area":"agents"},{"id":"2509.05755","title":"Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment","created":"2025-09-06","cited_by_count":5,"area":"agents"},{"id":"2510.07505","title":"PEAR: Planner-Executor Agent Robustness Benchmark","created":"2025-10-08","cited_by_count":5,"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":"2602.19547","title":"CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents","created":"2026-02-23","cited_by_count":5,"area":"agents"},{"id":"2512.16279","title":"QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems","created":"2025-12-18","cited_by_count":4,"area":"agents"},{"id":"2512.22211","title":"With Great Capabilities Come Great Responsibilities: Introducing the Agentic Risk & Capability Framework for Governing Agentic AI Systems","created":"2025-12-22","cited_by_count":4,"area":"agents"},{"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":"2505.23634","title":"MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment","created":"2025-05-29","cited_by_count":3,"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":"2602.15945","title":"From Tool Orchestration to Code Execution: A Study of MCP Design Choices","created":"2026-02-17","cited_by_count":3,"area":"agents"},{"id":"2603.04469","title":"Cross-Layer Semantic Flow Reconstruction for Attack Detection in Agentic Systems","created":"2026-03-04","cited_by_count":3,"area":"agents"},{"id":"2604.09748","title":"Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward","created":"2026-04-10","cited_by_count":3,"area":"lr"},{"id":"2604.16321","title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2604.23459","title":"Architecture Matters for Multi-Agent Security","created":"2026-04-25","cited_by_count":3,"area":null},{"id":"2605.03952","title":"MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents","created":"2026-05-05","cited_by_count":3,"area":"agents"},{"id":"2608.12851","title":"Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents","created":"2026-08-13","cited_by_count":3,"area":"agents"},{"id":"2502.11853","title":"StructTransform: A Scalable Attack Surface for Safety-Aligned Large Language Models","created":"2025-02-17","cited_by_count":2,"area":"alignment"},{"id":"2507.19399","title":"Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2604.10392","title":"Intent-aligned Formal Specification Synthesis via Traceable Refinement","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2606.04051","title":"RUBAS: Rubric-Based Reinforcement Learning for Agent Safety","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2607.11698","title":"Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"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":"2511.13333","title":"AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2512.21236","title":"Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking","created":"2025-12-24","cited_by_count":1,"area":"safety"},{"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":"2605.08382","title":"SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization","created":"2026-05-08","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":"2607.04528","title":"Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents","created":"2026-07-05","cited_by_count":1,"area":"agents"},{"id":"2607.12406","title":"Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions","created":"2026-07-14","cited_by_count":1,"area":"agents"},{"id":"2608.04317","title":"Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2507.02057","title":"MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2509.17042","title":"Orchestrate, Generate, Reflect: A VLM-Based Multi-Agent Collaboration Framework for Automated Driving Policy Learning","created":"2025-09-21","cited_by_count":0,"area":"driving"},{"id":"2511.18114","title":"ASTRA: Agentic Steerability and Risk Assessment Framework","created":"2025-11-22","cited_by_count":0,"area":"agents"},{"id":"2604.23067","title":"Training a General Purpose Automated Red Teaming Model","created":"2026-04-24","cited_by_count":0,"area":"safety"},{"id":"2605.11029","title":"FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.28734","title":"Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests","created":"2026-05-27","cited_by_count":0,"area":"safety"},{"id":"2606.19380","title":"ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures","created":"2026-06-13","cited_by_count":0,"area":"agents"},{"id":"2606.24245","title":"AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming","created":"2026-06-23","cited_by_count":0,"area":"agents"},{"id":"2607.03968","title":"Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents","created":"2026-07-04","cited_by_count":0,"area":"agents"},{"id":"2607.05743","title":"The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2608.05560","title":"From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs","created":"2026-08-06","cited_by_count":0,"area":"safety"},{"id":"2608.09476","title":"ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.14876","title":"Workspace Topology as an Attack Vector in Agentic Coding Assistants","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2608.25817","title":"SkillShield: Prompt-Space Security Skills for LLM Coding Agents","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2609.09798","title":"CS-Guard: Benchmarking LLM Guardrails for Code Generation Security","created":"2026-09-09","cited_by_count":0,"area":"safety"},{"id":"2609.10762","title":"Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.28915","title":"On the Effectiveness of Kernel-Level Evidence for Agent Security","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2610.01936","title":"Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.13626","title":"SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.18206","title":"SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}