@inproceedings{ferreira-etal-2026-deepresearch,
title = "{D}eep{R}esearch Retail: Benchmarking Tool-Augmented Deep Research in the {E}-Commerce Domain",
author = "Ferreira, Rafael and
Palo, Flavio Di and
Lu, Huilin and
Jain, Ayush and
Aduri, Harsha",
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.26/",
pages = "386--409",
ISBN = "979-8-89176-394-4",
abstract = "Deep Research (DR) systems autonomously retrieve and synthesize information from web sources, however, industrial DR applications face a critical gap: effective integration of internal tools with web search. In this work, we introduce DeepResearch Retail, an evaluation framework grounded in real-world e-commerce data for assessing Deep Research with tools (DR+Tools) in realistic commercial settings. The framework evaluates both factual faithfulness and multidimensional response quality when reasoning over heterogeneous web and internal data sources.We further present Hybrid-ReAct, a multi-agent architecture that demonstrates how collaborative reasoning and tool use can produce evidence-grounded answers. Experimental results validate our framework{'}s utility, showing improvements in agent{'}s performance when leveraging web-page information and multi-agent specialization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferreira-etal-2026-deepresearch">
<titleInfo>
<title>DeepResearch Retail: Benchmarking Tool-Augmented Deep Research in the E-Commerce Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flavio</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Palo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huilin</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayush</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harsha</namePart>
<namePart type="family">Aduri</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>Deep Research (DR) systems autonomously retrieve and synthesize information from web sources, however, industrial DR applications face a critical gap: effective integration of internal tools with web search. In this work, we introduce DeepResearch Retail, an evaluation framework grounded in real-world e-commerce data for assessing Deep Research with tools (DR+Tools) in realistic commercial settings. The framework evaluates both factual faithfulness and multidimensional response quality when reasoning over heterogeneous web and internal data sources.We further present Hybrid-ReAct, a multi-agent architecture that demonstrates how collaborative reasoning and tool use can produce evidence-grounded answers. Experimental results validate our framework’s utility, showing improvements in agent’s performance when leveraging web-page information and multi-agent specialization.</abstract>
<identifier type="citekey">ferreira-etal-2026-deepresearch</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.26/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>386</start>
<end>409</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DeepResearch Retail: Benchmarking Tool-Augmented Deep Research in the E-Commerce Domain
%A Ferreira, Rafael
%A Palo, Flavio Di
%A Lu, Huilin
%A Jain, Ayush
%A Aduri, Harsha
%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 ferreira-etal-2026-deepresearch
%X Deep Research (DR) systems autonomously retrieve and synthesize information from web sources, however, industrial DR applications face a critical gap: effective integration of internal tools with web search. In this work, we introduce DeepResearch Retail, an evaluation framework grounded in real-world e-commerce data for assessing Deep Research with tools (DR+Tools) in realistic commercial settings. The framework evaluates both factual faithfulness and multidimensional response quality when reasoning over heterogeneous web and internal data sources.We further present Hybrid-ReAct, a multi-agent architecture that demonstrates how collaborative reasoning and tool use can produce evidence-grounded answers. Experimental results validate our framework’s utility, showing improvements in agent’s performance when leveraging web-page information and multi-agent specialization.
%U https://aclanthology.org/2026.acl-industry.26/
%P 386-409
Markdown (Informal)
[DeepResearch Retail: Benchmarking Tool-Augmented Deep Research in the E-Commerce Domain](https://aclanthology.org/2026.acl-industry.26/) (Ferreira et al., ACL 2026)
ACL