MAESTRO: Multi-Agent Evaluation Suite for Testing, Reliability, and Observability

TL;DR

MAESTRO is a comprehensive evaluation suite for testing and analyzing multi-agent systems, providing standardized tools and insights into their performance, reliability, and resource usage across different configurations.

Contribution

It introduces a unified framework for evaluating MAS, supporting diverse configurations, and offers empirical insights into factors affecting MAS performance and reliability.

Findings

MAS executions can be stable structurally but variable temporally

Architecture significantly influences resource use and reliability

Reproducibility and cost are mainly driven by MAS design, not models or tools

Abstract

We present MAESTRO, an evaluation suite for the testing, reliability, and observability of LLM-based MAS. MAESTRO standardizes MAS configuration and execution through a unified interface, supports integrating both native and third-party MAS via a repository of examples and lightweight adapters, and exports framework-agnostic execution traces together with system-level signals (e.g., latency, cost, and failures). We instantiate MAESTRO with 12 representative MAS spanning popular agentic frameworks and interaction patterns, and conduct controlled experiments across repeated runs, backend models, and tool configurations. Our case studies show that MAS executions can be structurally stable yet temporally variable, leading to substantial run-to-run variance in performance and reliability. We further find that MAS architecture is the dominant driver of resource profiles, reproducibility, and cost-latency-accuracy trade-off, often outweighing changes in backend models or tool settings. Overall, MAESTRO enables systematic evaluation and provides empirical guidance for designing and optimizing agentic systems.