Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&D Poland Submission for WMT2026

Adam Dobrowolski; Paweł Przybysz; Marcin Szymański; Paweł Przewłocki; Artur Janicki

Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&D Poland Submission for WMT2026

Adam Dobrowolski, Paweł Przybysz, Marcin Szymański, Paweł Przewłocki, Artur Janicki

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

We propose a method to improve machine translation quality by ensembling multiple large language models within a multi-agent framework. The method addresses the problem of ensembling models with different tokenizations by abstracting away from token-level representations and operating at the level of generated text. The approach integrates several established concepts in MT, including ensembling, quality estimation, and reranking into one translation system. The log-likelihood reranking applied in this paper significantly improves results, even without ensembling. Experimental results show improvements comparable to COMET-MBR.

Anthology ID:: 2026.wmt-main.64
Volume:: Proceedings of the Eleventh Conference on Machine Translation
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venues:: WMT | WS
SIG:: SIGMT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 1235–1247
Language:
URL:: https://aclanthology.org/2026.wmt-main.64/
DOI:
Bibkey:
Cite (ACL):: Adam Dobrowolski, Paweł Przybysz, Marcin Szymański, Paweł Przewłocki, and Artur Janicki. 2026. Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&D Poland Submission for WMT2026. In Proceedings of the Eleventh Conference on Machine Translation, pages 1235–1247, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&D Poland Submission for WMT2026 (Dobrowolski et al., WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.64.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{dobrowolski-etal-2026-relay,
    title = "Relay-{MT}: Multi-agent {LLM} Ensembling for Machine Translation {--} {S}amsung {R}{\&}{D} {P}oland Submission for {WMT}2026",
    author = "Dobrowolski, Adam  and
      Przybysz, Pawe{\l}  and
      Szyma{\'n}ski, Marcin  and
      Przew{\l}ocki, Pawe{\l}  and
      Janicki, Artur",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.wmt-main.64/",
    pages = "1235--1247",
    ISBN = "979-8-89176-474-3",
    abstract = "We propose a method to improve machine translation quality by ensembling multiple large language models within a multi-agent framework. The method addresses the problem of ensembling models with different tokenizations by abstracting away from token-level representations and operating at the level of generated text. The approach integrates several established concepts in MT, including ensembling, quality estimation, and reranking into one translation system. The log-likelihood reranking applied in this paper significantly improves results, even without ensembling. Experimental results show improvements comparable to COMET-MBR."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dobrowolski-etal-2026-relay">
    <titleInfo>
        <title>Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&amp;D Poland Submission for WMT2026</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Dobrowolski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paweł</namePart>
        <namePart type="family">Przybysz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marcin</namePart>
        <namePart type="family">Szymański</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paweł</namePart>
        <namePart type="family">Przewłocki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Artur</namePart>
        <namePart type="family">Janicki</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 Eleventh Conference on Machine Translation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Barry</namePart>
            <namePart type="family">Haddow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tom</namePart>
            <namePart type="family">Kocmi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Philipp</namePart>
            <namePart type="family">Koehn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christof</namePart>
            <namePart type="family">Monz</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">979-8-89176-474-3</identifier>
    </relatedItem>
    <abstract>We propose a method to improve machine translation quality by ensembling multiple large language models within a multi-agent framework. The method addresses the problem of ensembling models with different tokenizations by abstracting away from token-level representations and operating at the level of generated text. The approach integrates several established concepts in MT, including ensembling, quality estimation, and reranking into one translation system. The log-likelihood reranking applied in this paper significantly improves results, even without ensembling. Experimental results show improvements comparable to COMET-MBR.</abstract>
    <identifier type="citekey">dobrowolski-etal-2026-relay</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.64/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1235</start>
            <end>1247</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&D Poland Submission for WMT2026
%A Dobrowolski, Adam
%A Przybysz, Paweł
%A Szymański, Marcin
%A Przewłocki, Paweł
%A Janicki, Artur
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F dobrowolski-etal-2026-relay
%X We propose a method to improve machine translation quality by ensembling multiple large language models within a multi-agent framework. The method addresses the problem of ensembling models with different tokenizations by abstracting away from token-level representations and operating at the level of generated text. The approach integrates several established concepts in MT, including ensembling, quality estimation, and reranking into one translation system. The log-likelihood reranking applied in this paper significantly improves results, even without ensembling. Experimental results show improvements comparable to COMET-MBR.
%U https://aclanthology.org/2026.wmt-main.64/
%P 1235-1247

Download as File

Markdown (Informal)

[Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&D Poland Submission for WMT2026](https://aclanthology.org/2026.wmt-main.64/) (Dobrowolski et al., WMT 2026)

Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&D Poland Submission for WMT2026 (Dobrowolski et al., WMT 2026)

ACL

Adam Dobrowolski, Paweł Przybysz, Marcin Szymański, Paweł Przewłocki, and Artur Janicki. 2026. Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&D Poland Submission for WMT2026. In Proceedings of the Eleventh Conference on Machine Translation, pages 1235–1247, Budapest, Hungary. Association for Computational Linguistics.