Community Paper Reading: AgentArch - A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise

​Join our upcoming community paper reading, where we'll dive into the paper from ServiceNow: "AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise."

We're thrilled to host the paper's primary author — Tara Bogavelli, Associate Machine Learning Engineer at ServiceNow — who will walk us through the research and its implications. There will be a live Q&A session, so bring your questions!

The paper aims to help the limited empirical understanding of how different design dimensions interact within complex multi-agent systems by providing a comprehensive enterprise-specific benchmark evaluating 18 distinct agentic configurations across state-of-the-art large language models. It examines four critical agentic system dimensions: orchestration strategy, agent prompt implementation (ReAct versus function calling), memory architecture, and thinking tool integration.