{"total":84,"rows":[{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90,"area":"agents"},{"id":"2408.02232","title":"SpecRover: Code Intent Extraction via LLMs","created":"2024-08-05","cited_by_count":72,"area":"agents"},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2402.16965","title":"WIPI: A New Web Threat for LLM-Driven Web Agents","created":"2024-02-26","cited_by_count":51,"area":"agents"},{"id":"2604.20779","title":"SWE-chat: Coding Agent Interactions From Real Users in the Wild","created":"2026-04-22","cited_by_count":43,"area":"agents"},{"id":"2409.10737","title":"AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing","created":"2024-09-16","cited_by_count":35,"area":"agents"},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"area":"agents"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2511.04427","title":"Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects","created":"2025-11-06","cited_by_count":24,"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":"2508.20816","title":"Multi-Agent Penetration Testing AI for the Web","created":"2025-08-28","cited_by_count":20,"area":"agents"},{"id":"2410.12468","title":"Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios","created":"2024-10-16","cited_by_count":18,"area":"agents"},{"id":"2602.09185","title":"AIDev: Studying AI Coding Agents on GitHub","created":"2026-02-09","cited_by_count":17,"area":"agents"},{"id":"2509.22040","title":"\"Your AI, My Shell\": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors","created":"2025-09-26","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2503.12374","title":"Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios","created":"2025-03-16","cited_by_count":14,"area":"agents"},{"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":"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":"2601.13597","title":"AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development","created":"2026-01-20","cited_by_count":11,"area":"agents"},{"id":"2604.23338","title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","created":"2026-04-25","cited_by_count":11,"area":"agents"},{"id":"2508.17343","title":"Agentic AI for Software: thoughts from Software Engineering community","created":"2025-08-24","cited_by_count":10,"area":"agents"},{"id":"2510.02609","title":"RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents","created":"2025-10-02","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":"2408.10495","title":"How Well Do Large Language Models Serve as End-to-End Secure Code Agents for Python?","created":"2024-08-20","cited_by_count":7,"area":"agents"},{"id":"2601.00477","title":"Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub","created":"2026-01-01","cited_by_count":7,"area":"agents"},{"id":"2411.08881","title":"Can We Trust AI Agents? A Case Study of an LLM-Based Multi-Agent System for Ethical AI","created":"2024-10-25","cited_by_count":6,"area":"agents"},{"id":"2504.07461","title":"Achilles Heel of Distributed Multi-Agent Systems","created":"2025-04-10","cited_by_count":6,"area":"agents"},{"id":"2511.17330","title":"Agentic Verification of Software Systems","created":"2025-11-21","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":"2507.02976","title":"How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench","created":"2025-06-30","cited_by_count":5,"area":"agents"},{"id":"2509.25894","title":"Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities","created":"2025-09-30","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":"2605.22534","title":"Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study","created":"2026-05-21","cited_by_count":5,"area":"agents"},{"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":"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":"2503.07693","title":"Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"agents"},{"id":"2601.20106","title":"Are We All Using Agents the Same Way? An Empirical Study of Core and Peripheral Developers Use of Coding Agents","created":"2026-01-27","cited_by_count":3,"area":"agents"},{"id":"2604.19354","title":"Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents in Capture the Flag Challenges","created":"2026-04-21","cited_by_count":3,"area":"agents"},{"id":"2606.13175","title":"The End of Code Review: Coding Agents Supersede Human Inspection","created":"2026-06-11","cited_by_count":3,"area":"agents"},{"id":"2607.25619","title":"SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents","created":"2026-07-28","cited_by_count":3,"area":"agents"},{"id":"2608.25776","title":"EVOMAL: Self-Poisoning in Self-Evolving Coding Agents","created":"2026-08-26","cited_by_count":3,"area":"agents"},{"id":"2605.06464","title":"To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study","created":"2026-05-07","cited_by_count":2,"area":"agents"},{"id":"2605.11891","title":"Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2406.16739","title":"Agent-Driven Automatic Software Improvement","created":"2024-06-24","cited_by_count":1,"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":"2511.20709","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":"2512.18080","title":"From Prompt to Product: A Human-Centered Benchmark of Agentic App Generation Systems","created":"2025-12-19","cited_by_count":1,"area":"agents"},{"id":"2602.10140","title":"Can Large Language Models Implement Agent-Based Models? An ODD-based Replication Study","created":"2026-02-08","cited_by_count":1,"area":"agents"},{"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":"2603.27524","title":"Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs","created":"2026-03-29","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":"2605.17548","title":"Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2605.29910","title":"Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents","created":"2026-05-28","cited_by_count":1,"area":"agents"},{"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":"2610.01023","title":"Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2511.11933","title":"InData: Towards Secure Multi-Step, Tool-Based Data Analysis","created":"2025-11-14","cited_by_count":0,"area":"agents"},{"id":"2511.20656","title":"Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support","created":"2025-10-10","cited_by_count":0,"area":"agents"},{"id":"2602.19021","title":"Trustworthy AI LLM Scalability Risk Index (LSRI): A Cybersecurity Framework Assessing Agentic-AI Security & Software Model Supply Chain Safety Boosting AI-Generated Malware Defense & Explainability Mitigating Emerging Risks of Generative AI","created":"2026-02-22","cited_by_count":0,"area":"agents"},{"id":"2604.09682","title":"Decision-Theoretic Safety Assessment of Persona-Driven Multi-Agent Systems in O-RAN","created":"2026-04-03","cited_by_count":0,"area":"agents"},{"id":"2604.23940","title":"Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery","created":"2026-04-27","cited_by_count":0,"area":"agents"},{"id":"2605.11027","title":"From Code-Centric to Intent-Centric Software Engineering: A Reflexive Thematic Analysis of Generative AI, Agentic Systems, and Engineering Accountability","created":"2026-05-10","cited_by_count":0,"area":"agents"},{"id":"2605.21453","title":"Quality and Security Signals in AI-Generated Python Refactoring Pull Requests","created":"2026-05-20","cited_by_count":0,"area":"agents"},{"id":"2606.15283","title":"AI-driven Software Development: A Pragmatic Path to Agentic Development Processes","created":"2026-06-13","cited_by_count":0,"area":"agents"},{"id":"2606.20243","title":"Phoenix: Safe GitHub Issue Resolution via Multi-Agent LLMs","created":"2026-06-18","cited_by_count":0,"area":"agents"},{"id":"2606.20615","title":"Specifying AI-SDLC Processes: A Protocol Language for Human-Agent Boundaries","created":"2026-05-24","cited_by_count":0,"area":"agents"},{"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":"2607.01810","title":"Decoupling Code Complexity from Newcomer Participation: A Causal Study of AI Coding Agent Adoption in OSS","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.05677","title":"From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.09586","title":"TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI Systems","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2607.09902","title":"Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic Code","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2607.12340","title":"Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents","created":"2026-07-14","cited_by_count":0,"area":"agents"},{"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":"2609.04711","title":"Building a research-software catalog with a coding agent: from hackathon prototype to public deployment","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.15963","title":"Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.17598","title":"Not All Agents Are Equal: Code Quality and Post-Merge Maintenance Across Five Autonomous Coding Agents in the Wild","created":"2026-09-12","cited_by_count":0,"area":"agents"},{"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":"2609.18298","title":"A Study of the Reliability of Agentic AI-Generated Programs","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.33371","title":"API Secrets Should Never Become Tokens in the LLM's Vocabulary: A Threat Analysis of API Credential Handling in LLM Agent Systems and an Empirical Evaluation of a Vault-Mediated Execution Boundary","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.05793","title":"Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.06163","title":"Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"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":"2610.14968","title":"SEEK: Agentic Knowledge Graph Retrieval for Secure Code Generation","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}