{"total":20,"rows":[{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469,"area":"agents"},{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152,"area":"agents"},{"id":"2410.22457","title":"Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Dataset","created":"2024-10-29","cited_by_count":24,"area":"agents"},{"id":"2502.19175","title":"MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis","created":"2025-02-26","cited_by_count":23,"area":"agents"},{"id":"2410.03225","title":"AutoPenBench: Benchmarking Generative Agents for Penetration Testing","created":"2024-10-04","cited_by_count":21,"area":"agents"},{"id":"2603.01045","title":"Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems","created":"2026-03-01","cited_by_count":20,"area":"agents"},{"id":"2412.05449","title":"Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications","created":"2024-12-06","cited_by_count":19,"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":"2505.15935","title":"MAPS: A Multilingual Benchmark for Agent Performance and Security","created":"2025-05-21","cited_by_count":7,"area":"agents"},{"id":"2602.02196","title":"TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents","created":"2026-02-02","cited_by_count":7,"area":"agents"},{"id":"2602.06714","title":"PrefIx: Understand and Adapt to User Preference in Human-Agent Interaction","created":"2026-02-06","cited_by_count":7,"area":"agents"},{"id":"2504.01495","title":"Are Autonomous Web Agents Good Testers?","created":"2025-04-02","cited_by_count":6,"area":"agents"},{"id":"2604.07733","title":"CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V","created":"2026-04-09","cited_by_count":2,"area":"agents"},{"id":"2605.12729","title":"Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2605.29893","title":"Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2608.20563","title":"Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents","created":"2026-08-20","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":"2609.09647","title":"Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery","created":"2026-09-09","cited_by_count":1,"area":"agents"},{"id":"2605.18597","title":"Latent Action Reparameterization for Efficient Agent Inference","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2609.08216","title":"Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI","created":"2026-09-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}