{"total":58,"rows":[{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564,"area":"agents"},{"id":"2503.18813","title":"Defeating Prompt Injections by Design","created":"2025-03-24","cited_by_count":297,"area":"agents"},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2402.18679","title":"Data Interpreter: An LLM Agent For Data Science","created":"2024-02-28","cited_by_count":225,"area":"agents"},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205,"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":"2401.05507","title":"InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks","created":"2024-01-10","cited_by_count":140,"area":"agents"},{"id":"2602.20867","title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","created":"2026-02-24","cited_by_count":130,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2604.06132","title":"Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents","created":"2026-04-07","cited_by_count":64,"area":"agents"},{"id":"2405.08355","title":"Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark","created":"2024-05-14","cited_by_count":63,"area":"agents"},{"id":"2405.14767","title":"FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models","created":"2024-05-23","cited_by_count":40,"area":"agents"},{"id":"2501.06706","title":"AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds","created":"2025-01-12","cited_by_count":40,"area":"agents"},{"id":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33,"area":"agents"},{"id":"2407.17535","title":"LAMBDA: A Large Model Based Data Agent","created":"2024-07-24","cited_by_count":30,"area":"agents"},{"id":"2503.11069","title":"API Agents vs. GUI Agents: Divergence and Convergence","created":"2025-03-14","cited_by_count":29,"area":"agents"},{"id":"2402.15809","title":"Empowering Large Language Model Agents through Action Learning","created":"2024-02-24","cited_by_count":22,"area":"agents"},{"id":"2412.14222","title":"A Survey on Large Language Model-based Agents for Statistics and Data Science","created":"2024-12-18","cited_by_count":22,"area":"agents"},{"id":"2408.15247","title":"AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems","created":"2024-08-09","cited_by_count":20,"area":"agents"},{"id":"2505.18646","title":"SEW: Self-Evolving Agentic Workflows for Automated Code Generation","created":"2025-05-24","cited_by_count":20,"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":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"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":"2504.16563","title":"Enhancing LLM-Based Agents via Global Planning and Hierarchical Execution","created":"2025-04-23","cited_by_count":13,"area":"agents"},{"id":"2604.28139","title":"Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows","created":"2026-04-30","cited_by_count":13,"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":"2404.18074","title":"MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot","created":"2024-04-28","cited_by_count":8,"area":"agents"},{"id":"2503.07044","title":"DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation","created":"2025-03-10","cited_by_count":8,"area":"agents"},{"id":"2511.11332","title":"UFO3: Weaving the Digital Agent Galaxy","created":"2025-11-14","cited_by_count":6,"area":"agents"},{"id":"2510.10074","title":"StepFly: Agentic Troubleshooting Guide Automation for Incident Diagnosis","created":"2025-10-11","cited_by_count":5,"area":"agents"},{"id":"2606.18051","title":"Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose","created":"2026-06-16","cited_by_count":5,"area":"agents"},{"id":"2504.04855","title":"BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents","created":"2025-04-07","cited_by_count":4,"area":"agents"},{"id":"2508.16678","title":"Cognitive Agents Powered by Large Language Models for Agile Software Project Management","created":"2025-08-21","cited_by_count":4,"area":"agents"},{"id":"2509.18661","title":"Agentic AutoSurvey: Let LLMs Survey LLMs","created":"2025-09-23","cited_by_count":4,"area":"agents"},{"id":"2601.16356","title":"The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes","created":"2026-01-22","cited_by_count":4,"area":"agents"},{"id":"2605.30434","title":"LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2601.01569","title":"CaveAgent: Transforming LLMs into Stateful Runtime Operators","created":"2026-01-04","cited_by_count":3,"area":"agents"},{"id":"2601.19793","title":"CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing","created":"2026-01-27","cited_by_count":3,"area":"agents"},{"id":"2605.16508","title":"The Scaling Laws of Skills in LLM Agent Systems","created":"2026-05-15","cited_by_count":3,"area":"agents"},{"id":"2607.20709","title":"NVIDIA-labs OO Agents: Native Python Object-Oriented Agents","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2511.03023","title":"PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2604.26805","title":"Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations","created":"2026-04-29","cited_by_count":2,"area":"agents"},{"id":"2501.19056","title":"Enabling Autonomic Microservice Management through Self-Learning Agents","created":"2025-01-31","cited_by_count":1,"area":"agents"},{"id":"2502.11197","title":"CSP: A Simulator For Multi-Agent Ranking Competitions","created":"2025-02-16","cited_by_count":1,"area":"agents"},{"id":"2505.18214","title":"LA-RCS: LLM-Agent-Based Robot Control System","created":"2025-05-23","cited_by_count":1,"area":"agents"},{"id":"2605.00827","title":"Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol","created":"2026-03-13","cited_by_count":1,"area":"agents"},{"id":"2605.15204","title":"SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatch","created":"2026-04-20","cited_by_count":1,"area":"agents"},{"id":"2606.28925","title":"Multi-Agent Routing as Set-Valued Prediction: A WildChat Benchmark and Cost-Aware Evaluation","created":"2026-06-27","cited_by_count":1,"area":"agents"},{"id":"2606.31423","title":"DA-Studio: An Agentic System for End-to-End Data Analysis","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.16617","title":"DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines","created":"2026-07-18","cited_by_count":1,"area":"agents"},{"id":"2509.14382","title":"Detecting Pipeline Failures through Fine-Grained Analysis of Web Agents","created":"2025-09-17","cited_by_count":0,"area":"agents"},{"id":"2602.05353","title":"AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2604.12421","title":"Agentic Insight Generation in VSM Simulations","created":"2026-04-14","cited_by_count":0,"area":"agents"},{"id":"2604.16646","title":"Agentic Frameworks for Reasoning Tasks: An Empirical Study","created":"2026-04-17","cited_by_count":0,"area":"agents"},{"id":"2605.10223","title":"Beyond Autonomy: A Dynamic Tiered AgentRunner Framework for Governable and Resilient Enterprise AI Execution","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2607.11042","title":"BackendForge: Benchmarking Agentic End-to-End Code Generation with Backend Services","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2608.21310","title":"Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2610.18507","title":"The Last Mile of Coding Agents for Long-Document Tasks: An Empirical Study on Clinical Trial Protocol Digitization","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}