{"total":29,"rows":[{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2512.04123","title":"Measuring Agents in Production","created":"2025-12-02","cited_by_count":37,"area":"agents"},{"id":"2604.05172","title":"ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces","created":"2026-04-06","cited_by_count":33,"area":"agents"},{"id":"2506.03828","title":"AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance","created":"2025-06-04","cited_by_count":15,"area":"agents"},{"id":"2603.00468","title":"Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems","created":"2026-02-28","cited_by_count":15,"area":"agents"},{"id":"2507.11277","title":"Taming Uncertainty via Automation: Observing, Analyzing, and Optimizing Agentic AI Systems","created":"2025-07-15","cited_by_count":12,"area":"agents"},{"id":"2605.07161","title":"SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2512.02228","title":"STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Calls","created":"2025-12-01","cited_by_count":4,"area":"agents"},{"id":"2604.01532","title":"PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools","created":"2026-04-02","cited_by_count":4,"area":"agents"},{"id":"2607.28545","title":"ORCA-bench: How Ready Are Language Model Agents for Oncall?","created":"2026-07-30","cited_by_count":4,"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":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2604.23455","title":"CUJBench: Benchmarking LLM-Agent on Cross-Modal Failure Diagnosis from Browser to Backend","created":"2026-04-25","cited_by_count":1,"area":"agents"},{"id":"2605.15425","title":"Runtime-Structured Task Decomposition for Agentic Coding Systems","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2606.29193","title":"A Multi-Dataset Benchmark for Evaluating LLM Agents in Microservice Failure Diagnosis","created":"2026-06-28","cited_by_count":1,"area":"agents"},{"id":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2609.30345","title":"Coding Agents Aren't Enough! Evaluating an Enterprise Security Brain for Agentic Cloud Investigations","created":"2026-09-24","cited_by_count":1,"area":"agents"},{"id":"2507.06396","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","created":"2025-07-08","cited_by_count":0,"area":"agents"},{"id":"2603.22083","title":"A Context Engineering Framework for Improving Enterprise AI Agents based on Digital-Twin MDP","created":"2026-03-23","cited_by_count":0,"area":"agents"},{"id":"2605.10384","title":"Agentic Performance at the Edge: Insights from Benchmarking","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2607.22563","title":"Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2607.25883","title":"Towards a Systems Foundation for Agentic Cloud Management","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2607.29405","title":"Beyond Component Testing: Validating Agentic AI Systems","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2608.28790","title":"ASTRA - Agentic System for Ticket Resolution and Analysis","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.14413","title":"A Hybrid Dependency-Aware Framework for Task Decomposition and Dynamic Agent Generation in Oracle-to-PostgreSQL Migration","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.27571","title":"FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.35427","title":"LLMs are General Asynchronous Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.00648","title":"Incident-Arena: Getting agents to the last nine of reliability","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}