{"total":126,"rows":[{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2502.14847","title":"Red-Teaming LLM Multi-Agent Systems via Communication Attacks","created":"2025-02-20","cited_by_count":122,"area":"agents"},{"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":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82,"area":"agents"},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2507.02554","title":"AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench","created":"2025-07-03","cited_by_count":71,"area":"agents"},{"id":"2411.00622","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","created":"2024-11-01","cited_by_count":61,"area":"agents"},{"id":"2409.16165","title":"EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities","created":"2024-09-24","cited_by_count":52,"area":"agents"},{"id":"2509.23586","title":"Reducing Cost of LLM Agents with Trajectory Reduction","created":"2025-09-28","cited_by_count":48,"area":"agents"},{"id":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46,"area":"agents"},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"area":"agents"},{"id":"2411.12924","title":"Human-In-the-Loop Software Development Agents","created":"2024-11-19","cited_by_count":42,"area":"agents"},{"id":"2509.09734","title":"MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools","created":"2025-09-10","cited_by_count":32,"area":"agents"},{"id":"2602.07274","title":"TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents","created":"2026-02-06","cited_by_count":29,"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":"2410.14209","title":"Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents","created":"2024-10-18","cited_by_count":26,"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":"2508.02744","title":"Large Language Model-based Data Science Agent: A Survey","created":"2025-08-02","cited_by_count":23,"area":"agents"},{"id":"2602.10999","title":"CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion","created":"2026-02-11","cited_by_count":23,"area":"agents"},{"id":"2508.13143","title":"Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks","created":"2025-08-18","cited_by_count":20,"area":"agents"},{"id":"2412.18371","title":"Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents","created":"2024-12-24","cited_by_count":16,"area":"agents"},{"id":"2604.09297","title":"SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering","created":"2026-04-10","cited_by_count":15,"area":"agents"},{"id":"2605.03378","title":"ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection","created":"2026-05-05","cited_by_count":14,"area":"agents"},{"id":"2512.15834","title":"Optimizing Agentic Language Model Inference via Speculative Tool Calls","created":"2025-12-17","cited_by_count":13,"area":"agents"},{"id":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","cited_by_count":11,"area":"agents"},{"id":"2412.17146","title":"LLM Agent for Fire Dynamics Simulations","created":"2024-12-22","cited_by_count":10,"area":"agents"},{"id":"2505.20749","title":"Can Agents Fix Agent Issues?","created":"2025-05-27","cited_by_count":9,"area":"agents"},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"id":"2506.09420","title":"A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy","created":"2025-06-11","cited_by_count":9,"area":"agents"},{"id":"2509.00616","title":"TimeCopilot","created":"2025-08-30","cited_by_count":9,"area":"agents"},{"id":"2505.12594","title":"AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection","created":"2025-05-19","cited_by_count":8,"area":"agents"},{"id":"2607.12747","title":"Tracing Agentic Failure from the Flow of Success","created":"2026-07-14","cited_by_count":8,"area":"agents"},{"id":"2511.00872","title":"A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks","created":"2025-11-02","cited_by_count":7,"area":"agents"},{"id":"2601.05777","title":"EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents","created":"2026-01-09","cited_by_count":7,"area":"agents"},{"id":"2605.12913","title":"Revisiting DAgger in the Era of LLM-Agents","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2504.13472","title":"CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation","created":"2025-04-18","cited_by_count":6,"area":"agents"},{"id":"2506.02546","title":"To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems","created":"2025-06-03","cited_by_count":6,"area":"agents"},{"id":"2509.13471","title":"An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software","created":"2025-09-16","cited_by_count":6,"area":"agents"},{"id":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2510.23761","title":"TDFlow: Agentic Workflows for Test Driven Development","created":"2025-10-27","cited_by_count":6,"area":"agents"},{"id":"2511.21572","title":"BAMAS: Structuring Budget-Aware Multi-Agent Systems","created":"2025-11-26","cited_by_count":6,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2601.15232","title":"When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling","created":"2026-01-21","cited_by_count":6,"area":"agents"},{"id":"2607.21217","title":"ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2502.09787","title":"TableTalk: Scaffolding Spreadsheet Development with a Language Agent","created":"2025-02-13","cited_by_count":5,"area":"agents"},{"id":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2512.02321","title":"LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems","created":"2025-12-02","cited_by_count":5,"area":"agents"},{"id":"2512.11143","title":"Automated Penetration Testing with LLM Agents and Classical Planning","created":"2025-12-11","cited_by_count":5,"area":"agents"},{"id":"2604.00917","title":"Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time","created":"2026-04-01","cited_by_count":5,"area":"agents"},{"id":"2607.03691","title":"Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality","created":"2026-07-04","cited_by_count":5,"area":"agents"},{"id":"2510.10460","title":"Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation","created":"2025-10-12","cited_by_count":4,"area":"agents"},{"id":"2511.19635","title":"Agint: Agentic Graph Compilation for Software Engineering Agents","created":"2025-11-24","cited_by_count":4,"area":"agents"},{"id":"2603.05744","title":"CodeScout: Contextual Problem Statement Enhancement for Software Agents","created":"2026-03-05","cited_by_count":4,"area":"agents"},{"id":"2605.25707","title":"AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions","created":"2026-05-25","cited_by_count":4,"area":"agents"},{"id":"2503.22512","title":"Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement","created":"2025-03-28","cited_by_count":3,"area":"agents"},{"id":"2511.08475","title":"Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale","created":"2025-11-11","cited_by_count":3,"area":"agents"},{"id":"2602.00592","title":"DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder","created":"2026-01-31","cited_by_count":3,"area":"agents"},{"id":"2602.21806","title":"Where Agent Frameworks Fall Short: Examining Functional Challenges and Usability Concerns","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2603.20260","title":"ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics","created":"2026-03-12","cited_by_count":3,"area":"agents"},{"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":"2604.16335","title":"Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents","created":"2026-03-13","cited_by_count":3,"area":"agents"},{"id":"2505.19489","title":"Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults","created":"2025-05-26","cited_by_count":2,"area":"agents"},{"id":"2508.12232","title":"LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery","created":"2025-08-17","cited_by_count":2,"area":"agents"},{"id":"2511.02399","title":"Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Framework","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2511.19536","title":"AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents","created":"2025-11-24","cited_by_count":2,"area":"agents"},{"id":"2512.23844","title":"From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering","created":"2025-12-29","cited_by_count":2,"area":"agents"},{"id":"2604.02665","title":"AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits","created":"2026-04-03","cited_by_count":2,"area":"agents"},{"id":"2604.07341","title":"ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2604.15468","title":"The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE","created":"2026-04-16","cited_by_count":2,"area":"agents"},{"id":"2605.20456","title":"Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development","created":"2026-05-19","cited_by_count":2,"area":"agents"},{"id":"2606.26614","title":"HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization","created":"2026-06-25","cited_by_count":2,"area":"agents"},{"id":"2607.00911","title":"From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.10856","title":"How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"id":"2607.18213","title":"SWE-Pruner Pro: The Coder LLM Already Knows What to Prune","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2608.02642","title":"MDArena: Evaluating Coding Agents on Realistic Molecular Dynamics Workflows","created":"2026-07-31","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":"2608.08413","title":"Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications","created":"2026-08-09","cited_by_count":2,"area":"agents"},{"id":"2503.13279","title":"Goal2Story: A Multi-Agent Fleet based on Privately Enabled sLLMs for Impacting Mapping on Requirements Elicitation","created":"2025-03-17","cited_by_count":1,"area":"agents"},{"id":"2510.02694","title":"MALF: A Multi-Agent LLM Framework for Intelligent Fuzzing of Industrial Control Protocols","created":"2025-10-03","cited_by_count":1,"area":"agents"},{"id":"2511.18249","title":"LLM Assisted Coding with Metamorphic Specification Mutation Agent","created":"2025-11-23","cited_by_count":1,"area":"agents"},{"id":"2512.11589","title":"A Study of Library Usage in Agent-Authored Pull Requests","created":"2025-12-12","cited_by_count":1,"area":"agents"},{"id":"2601.12148","title":"Many Hands Make Light Work: An LLM-based Multi-Agent System for Detecting Malicious PyPI Packages","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2602.02138","title":"CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems","created":"2026-02-02","cited_by_count":1,"area":"agents"},{"id":"2604.17699","title":"SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM Agents","created":"2026-04-20","cited_by_count":1,"area":"agents"},{"id":"2604.24212","title":"Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2605.18684","title":"Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents","created":"2026-05-18","cited_by_count":1,"area":"agents"},{"id":"2605.20548","title":"What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2605.26178","title":"ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2606.28791","title":"From Determinism to Delegation: AI-Native Software Engineering and the Evolution of the Agentic Engineer","created":"2026-06-27","cited_by_count":1,"area":"agents"},{"id":"2607.01211","title":"Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.07593","title":"What Makes a Good Bug Report for an AI Agent?","created":"2026-07-08","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":"2608.05959","title":"AgentExecutor: Partial Code Execution via Agentic Context Generation","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2608.11965","title":"Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2609.34712","title":"RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2609.36490","title":"LLMs Learn to Evade Latent Monitors from Prior Feedback Alone","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2507.15885","title":"ADEPTS: A Capability Framework for Human-Centered Agent Design","created":"2025-07-18","cited_by_count":0,"area":"agents"},{"id":"2507.16037","title":"A Pilot Study on LLM-Based Agentic Translation from Android to iOS: Pitfalls and Insights","created":"2025-07-21","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}