@inproceedings{wang-zhang-2026-knowing,
title = "Knowing What to Solve Before How: Preplan Empowered {LLM} Mathematical Reasoning",
author = "Wang, Shaojie and
Zhang, Liang",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.171/",
pages = "3608--3623",
ISBN = "979-8-89176-462-0",
abstract = "Current plan-based reasoning methods improve large language models (LLMs) by inserting a planning stage before execution, giving rise to the **question $\rightarrow$ plan $\rightarrow$ cot** paradigm. While effective, a closer examination reveals an inherent paradigm-level gap: both the planning and its execution stages decide *how to solve* a problem, while the prior question of *what to solve*; recognizing the problem type, the applicable tools, and the foreseeable pitfalls; remains entirely implicit. To bridge this gap, we propose **PPC** (**P**replan-**P**lan-**C**oT), a framework that introduces an explicit problem-understanding stage, the *preplan*, yielding a new **question $\rightarrow$ preplan $\rightarrow$ plan $\rightarrow$ cot** paradigm. Realizing this paradigm requires safeguarding the conceptual integrity of preplan at both ends. Specifically, we design a three-stage synthesis pipeline with a *spoiler-score detector* that filters out leakage and spoiler failures to build clean preplan supervision, and a composite GRPO reward enforces that the generated plan genuinely follows from the preplan. Experiments across four backbones and five mathematical reasoning benchmarks show that PPC achieves the best results on 39 of 40 metrics, improving *maj@16* and *pass@16* by +2.23 and +3.06 over the strongest baseline without introducing additional inference token overhead."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-zhang-2026-knowing">
<titleInfo>
<title>Knowing What to Solve Before How: Preplan Empowered LLM Mathematical Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shaojie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Current plan-based reasoning methods improve large language models (LLMs) by inserting a planning stage before execution, giving rise to the **question \rightarrow plan \rightarrow cot** paradigm. While effective, a closer examination reveals an inherent paradigm-level gap: both the planning and its execution stages decide *how to solve* a problem, while the prior question of *what to solve*; recognizing the problem type, the applicable tools, and the foreseeable pitfalls; remains entirely implicit. To bridge this gap, we propose **PPC** (**P**replan-**P**lan-**C**oT), a framework that introduces an explicit problem-understanding stage, the *preplan*, yielding a new **question \rightarrow preplan \rightarrow plan \rightarrow cot** paradigm. Realizing this paradigm requires safeguarding the conceptual integrity of preplan at both ends. Specifically, we design a three-stage synthesis pipeline with a *spoiler-score detector* that filters out leakage and spoiler failures to build clean preplan supervision, and a composite GRPO reward enforces that the generated plan genuinely follows from the preplan. Experiments across four backbones and five mathematical reasoning benchmarks show that PPC achieves the best results on 39 of 40 metrics, improving *maj@16* and *pass@16* by +2.23 and +3.06 over the strongest baseline without introducing additional inference token overhead.</abstract>
<identifier type="citekey">wang-zhang-2026-knowing</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.171/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3608</start>
<end>3623</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowing What to Solve Before How: Preplan Empowered LLM Mathematical Reasoning
%A Wang, Shaojie
%A Zhang, Liang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F wang-zhang-2026-knowing
%X Current plan-based reasoning methods improve large language models (LLMs) by inserting a planning stage before execution, giving rise to the **question \rightarrow plan \rightarrow cot** paradigm. While effective, a closer examination reveals an inherent paradigm-level gap: both the planning and its execution stages decide *how to solve* a problem, while the prior question of *what to solve*; recognizing the problem type, the applicable tools, and the foreseeable pitfalls; remains entirely implicit. To bridge this gap, we propose **PPC** (**P**replan-**P**lan-**C**oT), a framework that introduces an explicit problem-understanding stage, the *preplan*, yielding a new **question \rightarrow preplan \rightarrow plan \rightarrow cot** paradigm. Realizing this paradigm requires safeguarding the conceptual integrity of preplan at both ends. Specifically, we design a three-stage synthesis pipeline with a *spoiler-score detector* that filters out leakage and spoiler failures to build clean preplan supervision, and a composite GRPO reward enforces that the generated plan genuinely follows from the preplan. Experiments across four backbones and five mathematical reasoning benchmarks show that PPC achieves the best results on 39 of 40 metrics, improving *maj@16* and *pass@16* by +2.23 and +3.06 over the strongest baseline without introducing additional inference token overhead.
%U https://aclanthology.org/2026.findings-emnlp.171/
%P 3608-3623
Markdown (Informal)
[Knowing What to Solve Before How: Preplan Empowered LLM Mathematical Reasoning](https://aclanthology.org/2026.findings-emnlp.171/) (Wang & Zhang, Findings 2026)
ACL