{"total":22,"rows":[{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2409.03797","title":"NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls","created":"2024-09-04","cited_by_count":48,"area":"agents"},{"id":"2412.10133","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","created":"2024-12-13","cited_by_count":47,"area":"agents"},{"id":"2505.19443","title":"Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI","created":"2025-05-26","cited_by_count":42,"area":"agents"},{"id":"2504.20462","title":"TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native Systems","created":"2025-04-29","cited_by_count":13,"area":"agents"},{"id":"2603.14688","title":"AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent Systems","created":"2026-03-16","cited_by_count":7,"area":"agents"},{"id":"2507.22800","title":"The Multi-Agent Fault Localization System Based on Monte Carlo Tree Search Approach","created":"2025-07-30","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":"2508.20643","title":"CyberSleuth: Autonomous Blue-Team LLM Agent for Web Attack Forensics","created":"2025-08-28","cited_by_count":3,"area":"agents"},{"id":"2606.05395","title":"VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents","created":"2026-06-03","cited_by_count":3,"area":"agents"},{"id":"2602.04640","title":"Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents","created":"2026-02-04","cited_by_count":2,"area":"agents"},{"id":"2603.02345","title":"RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection","created":"2026-03-02","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":"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":"2607.01087","title":"Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering","created":"2026-07-01","cited_by_count":2,"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":"2604.11270","title":"Evaluating LLM Agents on Automated Software Analysis Tasks","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.06232","title":"Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2606.09637","title":"Agentic Persona Generation with Critique-Refinement: An Industrial Evaluation","created":"2026-06-08","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":"2608.25661","title":"From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis","created":"2026-08-26","cited_by_count":0,"area":"agents"}],"next_cursor":null}