@inproceedings{wang-2026-rethinking,
title = "Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms",
author = "Wang, Xinlin",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.123/",
pages = "1795--1807",
ISBN = "979-8-89176-394-4",
abstract = "Despite the impressive capabilities of large language models, their substantial computational costs, latency, and privacy risks hinder their widespread deployment in real-world applications. Small Language Models (SLMs) with fewer than 10 billion parameters present a promising alternative; however, their inherent limitations in knowledge and reasoning curtail their effectiveness. Existing research primarily focuses on enhancing SLMs through scaling laws or fine-tuning strategies while overlooking the potential of using agent paradigms, such as tool use and multi-agent collaboration, to systematically compensate for the inherent weaknesses of small models. To address this gap, this paper presents the first large-scale, comprehensive study of {\ensuremath{<}}10B open-source models under three paradigms: (1) the base model, (2) a single agent equipped with tools, and (3) a routing-based multi-agent system with collaborative capabilities.Our results show that structured agent frameworks (combining step-by-step reasoning and tool use) substantially improve effectiveness over direct prompting, with single-agent systems achieving the best balance between performance and cost. In contrast, routing-based multi-agent setups introduce additional coordination overhead with limited gains under small-model constraints.Our findings highlight the importance of agent-centric design for efficient and trustworthy deployment in resource-constrained settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-2026-rethinking">
<titleInfo>
<title>Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinlin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Despite the impressive capabilities of large language models, their substantial computational costs, latency, and privacy risks hinder their widespread deployment in real-world applications. Small Language Models (SLMs) with fewer than 10 billion parameters present a promising alternative; however, their inherent limitations in knowledge and reasoning curtail their effectiveness. Existing research primarily focuses on enhancing SLMs through scaling laws or fine-tuning strategies while overlooking the potential of using agent paradigms, such as tool use and multi-agent collaboration, to systematically compensate for the inherent weaknesses of small models. To address this gap, this paper presents the first large-scale, comprehensive study of \ensuremath<10B open-source models under three paradigms: (1) the base model, (2) a single agent equipped with tools, and (3) a routing-based multi-agent system with collaborative capabilities.Our results show that structured agent frameworks (combining step-by-step reasoning and tool use) substantially improve effectiveness over direct prompting, with single-agent systems achieving the best balance between performance and cost. In contrast, routing-based multi-agent setups introduce additional coordination overhead with limited gains under small-model constraints.Our findings highlight the importance of agent-centric design for efficient and trustworthy deployment in resource-constrained settings.</abstract>
<identifier type="citekey">wang-2026-rethinking</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.123/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1795</start>
<end>1807</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms
%A Wang, Xinlin
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F wang-2026-rethinking
%X Despite the impressive capabilities of large language models, their substantial computational costs, latency, and privacy risks hinder their widespread deployment in real-world applications. Small Language Models (SLMs) with fewer than 10 billion parameters present a promising alternative; however, their inherent limitations in knowledge and reasoning curtail their effectiveness. Existing research primarily focuses on enhancing SLMs through scaling laws or fine-tuning strategies while overlooking the potential of using agent paradigms, such as tool use and multi-agent collaboration, to systematically compensate for the inherent weaknesses of small models. To address this gap, this paper presents the first large-scale, comprehensive study of \ensuremath<10B open-source models under three paradigms: (1) the base model, (2) a single agent equipped with tools, and (3) a routing-based multi-agent system with collaborative capabilities.Our results show that structured agent frameworks (combining step-by-step reasoning and tool use) substantially improve effectiveness over direct prompting, with single-agent systems achieving the best balance between performance and cost. In contrast, routing-based multi-agent setups introduce additional coordination overhead with limited gains under small-model constraints.Our findings highlight the importance of agent-centric design for efficient and trustworthy deployment in resource-constrained settings.
%U https://aclanthology.org/2026.acl-industry.123/
%P 1795-1807
Markdown (Informal)
[Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms](https://aclanthology.org/2026.acl-industry.123/) (Wang, ACL 2026)
ACL