AI RESEARCH
General Agent Evaluation
arXiv CS.AI
•
ArXi:2602.22953v2 Announce Type: replace General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse unfamiliar environments. This is the first systematic study, comparing tool-calling, MCP, code-generation, and CLI agents on the same benchmarks with the same models.