{"total":19,"rows":[{"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":"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":"2607.02294","title":"Coding Agents Are Guessing: Measuring Action-Boundary Violations in Underspecified DevOps Instructions","created":"2026-07-02","cited_by_count":10,"area":"agents"},{"id":"2512.12791","title":"Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems","created":"2025-12-14","cited_by_count":8,"area":"agents"},{"id":"2510.04173","title":"Open Agent Specification (Agent Spec): A Unified Representation for AI Agents","created":"2025-10-05","cited_by_count":5,"area":"agents"},{"id":"2606.27154","title":"OpenRCA 2.0: From Outcome Labels to Causal Process Supervision","created":"2026-06-25","cited_by_count":5,"area":"agents"},{"id":"2512.13956","title":"AOI: Context-Aware Multi-Agent Operations via Dynamic Scheduling and Hierarchical Memory Compression","created":"2025-12-15","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":"2603.16110","title":"VIGIL: Towards Edge-Extended Agentic AI for Enterprise IT Support","created":"2026-03-17","cited_by_count":1,"area":"agents"},{"id":"2604.23366","title":"GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs","created":"2026-04-25","cited_by_count":1,"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":"2607.22563","title":"Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2608.14863","title":"Evaluating Agentic Code Repair Capabilities in Distributed Systems","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2608.16178","title":"Agent-Native Telemetry: Verifiable State-Delta Evidence for Autonomous Operations","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2608.24650","title":"Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2609.00050","title":"Towards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Harness","created":"2026-08-30","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}