{"ID":2871492,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.10769","arxiv_id":"2509.10769","title":"AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise","abstract":"While individual components of agentic architectures have been studied in isolation, there remains limited empirical understanding of how different design dimensions interact within complex multi-agent systems. This study aims to address these gaps by providing a comprehensive enterprise-specific benchmark evaluating 18 distinct agentic configurations across state-of-the-art large language models. We examine four critical agentic system dimensions: orchestration strategy, agent prompt implementation (ReAct versus function calling), memory architecture, and thinking tool integration. Our benchmark reveals significant model-specific architectural preferences that challenge the prevalent one-size-fits-all paradigm in agentic AI systems. It also reveals significant weaknesses in overall agentic performance on enterprise tasks with the highest scoring models achieving a maximum of only 35.3\\% success on the more complex task and 70.8\\% on the simpler task. We hope these findings inform the design of future agentic systems by enabling more empirically backed decisions regarding architectural components and model selection.","short_abstract":"While individual components of agentic architectures have been studied in isolation, there remains limited empirical understanding of how different design dimensions interact within complex multi-agent systems. This study aims to address these gaps by providing a comprehensive enterprise-specific benchmark evaluating 1...","url_abs":"https://arxiv.org/abs/2509.10769","url_pdf":"https://arxiv.org/pdf/2509.10769v2","authors":"[\"Tara Bogavelli\",\"Roshnee Sharma\",\"Hari Subramani\"]","published":"2025-09-13T01:18:23Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.MA\"]","methods":"[\"Language Model\"]","has_code":false}