Empirical Comparison of Agent Communication Protocols for Task Orchestration
This addresses a practical problem for enterprise AI developers by providing data-driven insights into protocol choices, though it is incremental as it compares existing approaches rather than introducing new ones.
This paper tackles the lack of empirical comparison between tool integration and inter-agent delegation protocols for AI agent systems by developing the first systematic benchmark across three complexity levels, quantifying trade-offs in response time, context window consumption, monetary cost, error recovery, and implementation complexity.
Context. Nowadays, artificial intelligence agent systems are transforming from single-tool interactions to complex multi-agent orchestrations. As a result, two competing communication protocols have emerged: a tool integration protocol that standardizes how agents invoke external tools, and an inter-agent delegation protocol that enables autonomous agents to discover and delegate tasks to one another. Despite widespread industry adoption by dozens of enterprise partners, no empirical comparison of these protocols exists in the literature. Objective. The goal of this work is to develop the first systematic benchmark comparing tool-integration-only, multi-agent delegation, and hybrid architectures across standardized queries at three complexity levels, and to quantify the trade-offs in response time, context window consumption, monetary cost, error recovery, and implementation complexity.