@inproceedings{bogavelli-etal-2026-agentarch,
title = "{A}gent{A}rch: A Benchmark for Evaluating Agent Architectures in Enterprise Workflows",
author = "Bogavelli, Tara and
Subramani, Hari and
Sharma, Roshnee",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.44/",
pages = "915--933",
ISBN = "979-8-89176-439-2",
abstract = "While individual components of agentic architectures have been studied in isolation, we lack empirical evidence on how design dimensions interact in realistic multi-agent systems. This study aims to address these gaps by providing a comprehensive enterprise-specific benchmark. We introduce AgentArch: a benchmark that evaluates 18 agentic configurations across state-of-the-art large language models. The study spans four dimensions: orchestration strategy, agent style (ReAct versus function calling), memory architecture, and thinking tool integration. Results reveal strong model-specific architectural preferences that challenge one-size-fits-all assumptions in agentic AI. They also expose notable performance gaps on enterprise tasks: the best models reach only 35.3{\%} success on the complex task and 70.8{\%} on the simpler task. We aim to inform architecting choices for enterprise agents by grounding model selection and component design in systematic evidence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bogavelli-etal-2026-agentarch">
<titleInfo>
<title>AgentArch: A Benchmark for Evaluating Agent Architectures in Enterprise Workflows</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tara</namePart>
<namePart type="family">Bogavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hari</namePart>
<namePart type="family">Subramani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roshnee</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>While individual components of agentic architectures have been studied in isolation, we lack empirical evidence on how design dimensions interact in realistic multi-agent systems. This study aims to address these gaps by providing a comprehensive enterprise-specific benchmark. We introduce AgentArch: a benchmark that evaluates 18 agentic configurations across state-of-the-art large language models. The study spans four dimensions: orchestration strategy, agent style (ReAct versus function calling), memory architecture, and thinking tool integration. Results reveal strong model-specific architectural preferences that challenge one-size-fits-all assumptions in agentic AI. They also expose notable performance gaps on enterprise tasks: the best models reach only 35.3% success on the complex task and 70.8% on the simpler task. We aim to inform architecting choices for enterprise agents by grounding model selection and component design in systematic evidence.</abstract>
<identifier type="citekey">bogavelli-etal-2026-agentarch</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.44/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>915</start>
<end>933</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AgentArch: A Benchmark for Evaluating Agent Architectures in Enterprise Workflows
%A Bogavelli, Tara
%A Subramani, Hari
%A Sharma, Roshnee
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F bogavelli-etal-2026-agentarch
%X While individual components of agentic architectures have been studied in isolation, we lack empirical evidence on how design dimensions interact in realistic multi-agent systems. This study aims to address these gaps by providing a comprehensive enterprise-specific benchmark. We introduce AgentArch: a benchmark that evaluates 18 agentic configurations across state-of-the-art large language models. The study spans four dimensions: orchestration strategy, agent style (ReAct versus function calling), memory architecture, and thinking tool integration. Results reveal strong model-specific architectural preferences that challenge one-size-fits-all assumptions in agentic AI. They also expose notable performance gaps on enterprise tasks: the best models reach only 35.3% success on the complex task and 70.8% on the simpler task. We aim to inform architecting choices for enterprise agents by grounding model selection and component design in systematic evidence.
%U https://aclanthology.org/2026.aacl-long.44/
%P 915-933
Markdown (Informal)
[AgentArch: A Benchmark for Evaluating Agent Architectures in Enterprise Workflows](https://aclanthology.org/2026.aacl-long.44/) (Bogavelli et al., AACL-IJCNLP 2026)
ACL
- Tara Bogavelli, Hari Subramani, and Roshnee Sharma. 2026. AgentArch: A Benchmark for Evaluating Agent Architectures in Enterprise Workflows. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 915–933, Hengqin, China. Association for Computational Linguistics.