<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bates-perera-2026-prompting">
    <titleInfo>
        <title>Prompting Strategies for Conceptual Ideation in Problem Solving</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chris</namePart>
        <namePart type="family">Bates</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ian</namePart>
        <namePart type="family">Perera</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>LLMs have improved at executing well-specified chains of reasoning but remain weak at conceptual ideation, which identifies what is worth reasoning about in the first place. We cast this as bilevel optimization over (i) a compact hypothesis space Θ\subseteqΘ₀ and (ii) a point θınΘ, and derive a domain-agnostic prompting strategy — Generate-Θ — that makes hypothesis-space construction an explicit pre-solving step. On two challenging puzzle domains, Generate-Θ matches or exceeds the max-thinking variant of the same base model (Claude Opus 4.6 or DeepSeek-v3.2/v4) and outperforms reasonable prompting baselines. These results suggest our method works well in tasks that are well-represented in the training set but nonetheless require creativity to solve new instances. Based on our formalism, we propose extensions for solving less familiar tasks as well. Results may provide insight into strategies learned by “reasoning” models during training. Our prompting strategy (or extensions thereof) could be integrated with RL training to produce better exploratory data for reasoning models in ideation-heavy tasks.</abstract>
    <identifier type="citekey">bates-perera-2026-prompting</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.97/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1389</start>
            <end>1403</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prompting Strategies for Conceptual Ideation in Problem Solving
%A Bates, Chris
%A Perera, Ian
%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 bates-perera-2026-prompting
%X LLMs have improved at executing well-specified chains of reasoning but remain weak at conceptual ideation, which identifies what is worth reasoning about in the first place. We cast this as bilevel optimization over (i) a compact hypothesis space Θ\subseteqΘ₀ and (ii) a point θınΘ, and derive a domain-agnostic prompting strategy — Generate-Θ — that makes hypothesis-space construction an explicit pre-solving step. On two challenging puzzle domains, Generate-Θ matches or exceeds the max-thinking variant of the same base model (Claude Opus 4.6 or DeepSeek-v3.2/v4) and outperforms reasonable prompting baselines. These results suggest our method works well in tasks that are well-represented in the training set but nonetheless require creativity to solve new instances. Based on our formalism, we propose extensions for solving less familiar tasks as well. Results may provide insight into strategies learned by “reasoning” models during training. Our prompting strategy (or extensions thereof) could be integrated with RL training to produce better exploratory data for reasoning models in ideation-heavy tasks.
%U https://aclanthology.org/2026.realm-1.97/
%P 1389-1403

Markdown (Informal)

[Prompting Strategies for Conceptual Ideation in Problem Solving](https://aclanthology.org/2026.realm-1.97/) (Bates & Perera, REALM 2026)

• Prompting Strategies for Conceptual Ideation in Problem Solving (Bates & Perera, REALM 2026)

ACL

• Chris Bates and Ian Perera. 2026. Prompting Strategies for Conceptual Ideation in Problem Solving. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 1389–1403, Budapest, Hungary. Association for Computational Linguistics.