<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hsu-etal-2026-rethinking">
    <titleInfo>
        <title>Rethinking Agentic Search with Piika: Is Lexical Retrieval Sufficient?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tz-Huan</namePart>
        <namePart type="family">Hsu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jheng-Hong</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yijun</namePart>
        <namePart type="family">Ge</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jimmy</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolai</namePart>
            <namePart type="family">Rozanov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maryam</namePart>
            <namePart type="family">Hashemzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akhil</namePart>
            <namePart type="family">Arora</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-485-9</identifier>
    </relatedItem>
    <abstract>Does a lexical retriever suffice as large language models (LLMs) become more capable within an agentic search loop? We revisit this question by pairing BM25 with increasingly capable LLMs and introduce Piika, a search agent equipped with three tools for retrieving, browsing, and reading documents. On the BrowseComp-Plus benchmark, under the same GPT-5 + BM25 setup, Piika improves the accuracy from 58.3% to 74.6% while reducing cost from $400 to $95. Despite relying only on lexical retrieval, it also outperforms the previously reported GPT-5 + dense-retriever setup, which achieves 73.0% accuracy at $361. Piika further scales with stronger LLMs, reaching 83.1% answer accuracy and 94.7% surfaced-evidence recall with GPT-5.5. Across model families, our results show that simple lexical retrieval, coupled with capable LLMs, a lightweight harness, and an effective tool interface, can remain highly competitive with more complex retrieval systems. Source code and evaluation artifacts are available at https://piika.ai.</abstract>
    <identifier type="citekey">hsu-etal-2026-rethinking</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.104/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1534</start>
            <end>1550</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Rethinking Agentic Search with Piika: Is Lexical Retrieval Sufficient?
%A Hsu, Tz-Huan
%A Yang, Jheng-Hong
%A Ge, Yijun
%A Lin, Jimmy
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F hsu-etal-2026-rethinking
%X Does a lexical retriever suffice as large language models (LLMs) become more capable within an agentic search loop? We revisit this question by pairing BM25 with increasingly capable LLMs and introduce Piika, a search agent equipped with three tools for retrieving, browsing, and reading documents. On the BrowseComp-Plus benchmark, under the same GPT-5 + BM25 setup, Piika improves the accuracy from 58.3% to 74.6% while reducing cost from $400 to $95. Despite relying only on lexical retrieval, it also outperforms the previously reported GPT-5 + dense-retriever setup, which achieves 73.0% accuracy at $361. Piika further scales with stronger LLMs, reaching 83.1% answer accuracy and 94.7% surfaced-evidence recall with GPT-5.5. Across model families, our results show that simple lexical retrieval, coupled with capable LLMs, a lightweight harness, and an effective tool interface, can remain highly competitive with more complex retrieval systems. Source code and evaluation artifacts are available at https://piika.ai.
%U https://aclanthology.org/2026.realm-1.104/
%P 1534-1550

Markdown (Informal)

[Rethinking Agentic Search with Piika: Is Lexical Retrieval Sufficient?](https://aclanthology.org/2026.realm-1.104/) (Hsu et al., REALM 2026)

• Rethinking Agentic Search with Piika: Is Lexical Retrieval Sufficient? (Hsu et al., REALM 2026)

ACL

• Tz-Huan Hsu, Jheng-Hong Yang, Yijun Ge, and Jimmy Lin. 2026. Rethinking Agentic Search with Piika: Is Lexical Retrieval Sufficient?. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 1534–1550, Budapest, Hungary. Association for Computational Linguistics.