{"total":14,"rows":[{"id":"2602.14878","title":"Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions","created":"2026-02-16","cited_by_count":17,"area":"agents"},{"id":"2512.01939","title":"An Empirical Study of Agent Developer Practices in AI Agent Frameworks","created":"2025-12-01","cited_by_count":14,"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":"2601.17581","title":"How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests","created":"2026-01-24","cited_by_count":8,"area":"agents"},{"id":"2601.00477","title":"Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub","created":"2026-01-01","cited_by_count":7,"area":"agents"},{"id":"2607.03691","title":"Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality","created":"2026-07-04","cited_by_count":5,"area":"agents"},{"id":"2601.19583","title":"Toward Architecture-Aware Evaluation Metrics for LLM Agents","created":"2026-01-27","cited_by_count":4,"area":"agents"},{"id":"2606.05548","title":"ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer","created":"2026-06-04","cited_by_count":2,"area":"agents"},{"id":"2607.10856","title":"How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"id":"2608.08413","title":"Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications","created":"2026-08-09","cited_by_count":2,"area":"agents"},{"id":"2604.16646","title":"Agentic Frameworks for Reasoning Tasks: An Empirical Study","created":"2026-04-17","cited_by_count":0,"area":"agents"},{"id":"2609.17698","title":"A Large-Scale Empirical Study of Quality Assurance Practices and Gaps in AI Agents","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.37864","title":"AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.04921","title":"Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}