{"total":21,"rows":[{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102,"area":"agents"},{"id":"2510.25445","title":"Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions","created":"2025-10-29","cited_by_count":48,"area":"agents"},{"id":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2411.13768","title":"Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture","created":"2024-11-21","cited_by_count":11,"area":"agents"},{"id":"2605.21404","title":"What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema","created":"2026-05-20","cited_by_count":6,"area":"agents"},{"id":"2605.16282","title":"Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2601.20617","title":"Agent Benchmarks Fail Public Sector Requirements","created":"2026-01-28","cited_by_count":3,"area":"agents"},{"id":"2609.09218","title":"The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean","created":"2026-09-06","cited_by_count":3,"area":"agents"},{"id":"2604.20200","title":"Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows","created":"2026-04-22","cited_by_count":2,"area":"agents"},{"id":"2606.00135","title":"On Effectiveness and Efficiency of Agentic Tool-calling and RL Training","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2606.19899","title":"Measuring Biological Capabilities and Risks of AI Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2607.01153","title":"Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2609.04667","title":"ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2609.18605","title":"PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?","created":"2026-09-16","cited_by_count":1,"area":"agents"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2605.24699","title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.01584","title":"Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2609.01271","title":"What Does an Agentic Software Engineering Benchmark Measure? Profiling Task Demands and Agent Behaviour Beyond What Category Labels Reveal","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.05527","title":"Beyond \"AI Helps Humans\": Decision-Targeted Evaluation Design for Human-Agent Teams in the Agentic Era","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.07712","title":"APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents","created":"2026-09-07","cited_by_count":0,"area":"agents"}],"next_cursor":null}