<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bystronski-etal-2026-beyond">
    <titleInfo>
        <title>Beyond Discrete Search: Divergent Thinking as Intention Optimization in Latent Space</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mateusz</namePart>
        <namePart type="family">Bystroński</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Grzegorz</namePart>
        <namePart type="family">Piotrowski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tomasz</namePart>
        <namePart type="given">Jan</namePart>
        <namePart type="family">Kajdanowicz</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">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="given">Diego</namePart>
            <namePart type="family">Rodriguez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ona</namePart>
            <namePart type="family">de Gibert</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, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-393-7</identifier>
    </relatedItem>
    <abstract>We argue that LLM-based coding agents frequently fail to solve problems that lie within the model’s capacity and the bottleneck is often the conditioning context rather than the model itself. We formalize this for the full class of Turing-computable problems with verifiable specifications and introduce a framework that recasts coding as optimization overconditioning contexts that influence the generation of natural-languagesolution intentions. Guided by execution feedback, the method searches thiscontinuous context space to steer a coding agent toward correct solutions. The method operates as a plug-in layer that can wrap any coding agent without modifying its architecture or weights. On SWE-Bench Verified, our method raises the resolution rate of a weak, quantized 24B open-weight model to parity with frontier models +25× its size.</abstract>
    <identifier type="citekey">bystronski-etal-2026-beyond</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-srw.88/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1007</start>
            <end>1016</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond Discrete Search: Divergent Thinking as Intention Optimization in Latent Space
%A Bystroński, Mateusz
%A Piotrowski, Grzegorz
%A Kajdanowicz, Tomasz Jan
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%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, United States
%@ 979-8-89176-393-7
%F bystronski-etal-2026-beyond
%X We argue that LLM-based coding agents frequently fail to solve problems that lie within the model’s capacity and the bottleneck is often the conditioning context rather than the model itself. We formalize this for the full class of Turing-computable problems with verifiable specifications and introduce a framework that recasts coding as optimization overconditioning contexts that influence the generation of natural-languagesolution intentions. Guided by execution feedback, the method searches thiscontinuous context space to steer a coding agent toward correct solutions. The method operates as a plug-in layer that can wrap any coding agent without modifying its architecture or weights. On SWE-Bench Verified, our method raises the resolution rate of a weak, quantized 24B open-weight model to parity with frontier models +25× its size.
%U https://aclanthology.org/2026.acl-srw.88/
%P 1007-1016

Markdown (Informal)

[Beyond Discrete Search: Divergent Thinking as Intention Optimization in Latent Space](https://aclanthology.org/2026.acl-srw.88/) (Bystroński et al., ACL 2026)

• Beyond Discrete Search: Divergent Thinking as Intention Optimization in Latent Space (Bystroński et al., ACL 2026)

ACL

• Mateusz Bystroński, Grzegorz Piotrowski, and Tomasz Jan Kajdanowicz. 2026. Beyond Discrete Search: Divergent Thinking as Intention Optimization in Latent Space. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 1007–1016, San Diego, California, United States. Association for Computational Linguistics.