Back to Details

paper-plan

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Paper Plan: From Review Conclusions to Paper Outline

论文规划：从评审结论到论文大纲

Generate a structured, section-by-section paper outline from: $ARGUMENTS
基于**$ARGUMENTS**生成分章节的结构化论文大纲

Constants

常量配置

  • REVIEWER_MODEL = 
    gpt-5.4
     — Model used via Codex MCP for outline review. Must be an OpenAI model.
  • TARGET_VENUE = 
    ICLR
     — Default venue. User can override (e.g., 
    /paper-plan "topic" — venue: NeurIPS
    ). Supported: 
    ICLR
    , 
    NeurIPS
    , 
    ICML
    .
  • MAX_PAGES — Main body page limit, measured from first page to end of Conclusion section (excluding references, appendix, and acknowledgements). ICLR=9, NeurIPS=9, ICML=8.
  • REVIEWER_MODEL = 
    gpt-5.4
     — 用于大纲评审的模型，通过Codex MCP调用，必须为OpenAI模型。
  • TARGET_VENUE = 
    ICLR
     — 默认目标会议。用户可自行覆盖（例如：
    /paper-plan "topic" — venue: NeurIPS
    ）。支持的会议包括：
    ICLR
    、
    NeurIPS
    、
    ICML
    。
  • MAX_PAGES — 正文页数限制，计算范围从第一页到结论部分末尾（不包含参考文献、附录和致谢）。ICLR=9页，NeurIPS=9页，ICML=8页。

Inputs

输入要求

The skill expects one or more of these in the project directory:
  1. NARRATIVE_REPORT.md or STORY.md — research narrative with claims and evidence
  2. GPT54_AUTO_REVIEW.md — auto-review loop conclusions
  3. Experiment results — JSON files in 
    figures/
    , screen logs, tables
  4. IDEA_REPORT.md — from idea-discovery pipeline (if applicable)
If none exist, ask the user to describe the paper's contribution in 3-5 sentences.
本功能期望项目目录中存在以下一种或多种文件：
  1. NARRATIVE_REPORT.md 或 STORY.md — 包含论点和证据的研究叙述文档
  2. GPT54_AUTO_REVIEW.md — 自动评审循环的结论文档
  3. 实验结果 — 存储在
    figures/
    目录下的JSON文件、屏幕日志、表格
  4. IDEA_REPORT.md — 来自创意发现流程的文档（如有）
如果上述文件均不存在，请要求用户用3-5句话描述论文的贡献。

Workflow

工作流程

Step 1: Extract Claims and Evidence

步骤1：提取论点与证据

Read all available narrative documents and extract:
  1. Core claims (3-5 main contributions)
  2. Evidence for each claim (which experiments, which metrics, which figures)
  3. Known weaknesses (from reviewer feedback)
  4. Suggested framing (from review conclusions)
Build a Claims-Evidence Matrix:
markdown
| Claim | Evidence | Status | Section |
|-------|----------|--------|---------|
| [claim 1] | [exp A, metric B] | Supported | §3.2 |
| [claim 2] | [exp C] | Partially supported | §4.1 |
读取所有可用的叙述文档，提取以下内容：
  1. 核心论点（3-5个主要贡献点）
  2. 论点对应的证据（涉及哪些实验、指标、图表）
  3. 已知不足（来自评审反馈）
  4. 建议框架（来自评审结论）
构建论点-证据矩阵：
markdown
| 论点 | 证据 | 状态 | 对应章节 |
|-------|----------|--------|---------|
| [论点1] | [实验A，指标B] | 已充分支撑 | §3.2 |
| [论点2] | [实验C] | 部分支撑 | §4.1 |

Step 2: Determine Paper Type and Structure

步骤2：确定论文类型与结构

Based on TARGET_VENUE and paper content, classify and select structure.
IMPORTANT: The section count is FLEXIBLE (5-8 sections). Choose what fits the content best. The templates below are starting points, not rigid constraints.
Empirical/Diagnostic paper:
1. Introduction (1.5 pages)
2. Related Work (1 page)
3. Method / Setup (1.5 pages)
4. Experiments (3 pages)
5. Analysis / Discussion (1 page)
6. Conclusion (0.5 pages)
Theory + Experiments paper:
1. Introduction (1.5 pages)
2. Related Work (1 page)
3. Preliminaries & Modeling (1.5 pages)
4. Experiments (1.5 pages)
5. Theory Part A (1.5 pages)
6. Theory Part B (1.5 pages)
7. Conclusion (0.5 pages)
— Total: 9 pages
Theory papers often need 7 sections (splitting theory into estimation + optimization, or setup + analysis). The total page budget MUST sum to MAX_PAGES.
Theory papers should:
  • Include proof sketch locations (not just theorem statements)
  • Plan a comparison table of prior theoretical bounds vs. this paper's bounds
  • Identify which proofs go in appendix vs. main body
Method paper:
1. Introduction (1.5 pages)
2. Related Work (1 page)
3. Method (2 pages)
4. Experiments (2.5 pages)
5. Ablation / Analysis (1 page)
6. Conclusion (0.5 pages)
根据TARGET_VENUE和论文内容，进行分类并选择合适的结构。
重要提示：章节数量可灵活调整（5-8章），选择最适配内容的结构。以下模板仅为参考框架，并非硬性约束。
实证/诊断类论文：
1. 引言（1.5页）
2. 相关工作（1页）
3. 方法/实验设置（1.5页）
4. 实验部分（3页）
5. 分析/讨论（1页）
6. 结论（0.5页）
理论+实验类论文：
1. 引言（1.5页）
2. 相关工作（1页）
3. 预备知识与建模（1.5页）
4. 实验部分（1.5页）
5. 理论模块A（1.5页）
6. 理论模块B（1.5页）
7. 结论（0.5页）
— 总页数：9页
理论类论文通常需要7个章节（将理论部分拆分为估计+优化，或设置+分析）。总页数必须严格符合MAX_PAGES限制。
理论类论文需满足：
  • 明确证明梗概的放置位置（不仅是定理陈述）
  • 规划现有理论边界与本文边界的对比表格
  • 确定哪些证明内容放在附录，哪些放在正文
方法类论文：
1. 引言（1.5页）
2. 相关工作（1页）
3. 方法介绍（2页）
4. 实验部分（2.5页）
5. 消融实验/分析（1页）
6. 结论（0.5页）

Step 3: Section-by-Section Planning

步骤3：分章节规划

For each section, specify:
markdown
undefined
针对每个章节，需明确以下内容：
markdown
undefined

§0 Abstract

§0 摘要

  • One-sentence problem: [what gap this paper addresses]
  • Approach: [what we do, in one sentence]
  • Key result: [most compelling quantitative finding]
  • Implication: [why it matters]
  • Estimated length: 150-250 words
  • Self-contained check: can a reader understand this without the paper?
  • 一句话问题定义：[本文解决的研究空白]
  • 研究方法：[核心方法的一句话概述]
  • 关键结果：[最具说服力的量化发现]
  • 研究意义：[该结果的重要性]
  • 预估篇幅：150-250词
  • 自洽性检查：读者无需阅读全文即可理解摘要内容？

§1 Introduction

§1 引言

  • Opening hook: [1-2 sentences that motivate the problem]
  • Gap: [what's missing in prior work]
  • Key questions: [the research questions this paper answers]
  • Contributions: [numbered list, matching Claims-Evidence Matrix]
  • Hero figure: [describe what Figure 1 should show — MUST include clear comparison if applicable]
  • Estimated length: 1.5 pages
  • Key citations: [3-5 papers to cite here]
  • 开篇引入：[1-2句激发问题动机的描述]
  • 研究空白：[现有工作中缺失的部分]
  • 核心研究问题：[本文要解答的研究问题]
  • 研究贡献：[编号列表，与论点-证据矩阵对应]
  • 核心图表：[描述图1应展示的内容 — 若适用，必须包含明确对比]
  • 预估篇幅：1.5页
  • 关键引用：[3-5篇需在此处引用的文献]

§2 Related Work

§2 相关工作

  • Subtopics: [2-4 categories of related work]
  • Positioning: [how this paper differs from each category]
  • Minimum length: 1 full page (at least 3-4 paragraphs with substantive synthesis)
  • Must NOT be just a list — synthesize, compare, and position
  • 子主题：[2-4类相关工作分类]
  • 定位分析：[本文与每类工作的差异]
  • 最低篇幅要求：至少1整页（至少3-4段有实质整合内容的段落）
  • 严禁简单罗列 — 需进行整合、对比和定位

§3 Method / Setup / Preliminaries

§3 方法/实验设置/预备知识

  • Notation: [key symbols and their meanings]
  • Problem formulation: [formal setup]
  • Method description: [algorithm, model, or experimental design]
  • Formal statements: [theorems, propositions if applicable]
  • Proof sketch locations: [which key steps appear here vs. appendix]
  • Estimated length: 1.5-2 pages
  • 符号定义：[核心符号及其含义]
  • 问题形式化：[正式的问题设置]
  • 方法描述：[算法、模型或实验设计]
  • 正式陈述：[定理、命题（如有）]
  • 证明梗概位置：[关键步骤放在正文还是附录]
  • 预估篇幅：1.5-2页

§4 Experiments / Main Results

§4 实验/核心结果

  • Figures planned:
    • Fig 1: [description, type: bar/line/table/architecture, WHAT COMPARISON it shows]
    • Fig 2: [description]
    • Table 1: [what it shows, which methods/baselines compared]
  • Data source: [which JSON files / experiment results]
  • 规划的图表：
    • 图1：[描述，类型：柱状图/折线图/表格/架构图，需展示的对比内容]
    • 图2：[描述]
    • 表1：[展示内容，对比的方法/基线]
  • 数据来源：[对应的JSON文件/实验结果]

§5 Conclusion

§5 结论

  • Restatement: [contributions rephrased, not copy-pasted from intro]
  • Limitations: [honest assessment — reviewers value this]
  • Future work: [1-2 concrete directions]
  • Estimated length: 0.5 pages
undefined
  • 贡献重述：[重新表述研究贡献，不可直接复制引言内容]
  • 研究局限：[诚实评估 — 评审员重视这一点]
  • 未来工作方向：[1-2个具体的研究方向]
  • 预估篇幅：0.5页
undefined

Step 4: Figure Plan

步骤4：图表规划

List every figure and table:
markdown
undefined
列出所有图表和表格：
markdown
undefined

Figure Plan

图表规划

IDTypeDescriptionData SourcePriority
Fig 1Hero/ArchitectureSystem overview + comparisonmanualHIGH
Fig 2Line plotTraining curves comparisonfigures/exp_A.jsonHIGH
Fig 3Bar chartAblation resultsfigures/ablation.jsonMEDIUM
Table 1Comparison tableMain results vs. baselinesfigures/main_results.jsonHIGH
Table 2Theory comparisonPrior bounds vs. oursmanualHIGH (theory papers)

**CRITICAL for Figure 1 / Hero Figure**: Describe in detail what the figure should contain, including:
- Which methods are being compared
- What the visual difference should demonstrate
- Caption draft that clearly states the comparison
编号类型描述数据来源优先级
图1核心架构图系统总览+对比手动绘制高
图2折线图训练曲线对比figures/exp_A.json高
图3柱状图消融实验结果figures/ablation.json中
表1对比表格核心结果与基线对比figures/main_results.json高
表2理论对比表现有边界与本文边界对比手动整理高（仅理论类论文）

**核心图/图1的关键要求**：详细描述图表应包含的内容，包括：
- 对比的方法
- 视觉上需体现的差异
- 清晰说明对比内容的标题草稿

Step 5: Citation Scaffolding

步骤5：引用框架搭建

For each section, list required citations:
markdown
undefined
针对每个章节，列出所需引用的文献：
markdown
undefined

Citation Plan

引用规划

  • §1 Intro: [paper1], [paper2], [paper3] (problem motivation)
  • §2 Related: [paper4]-[paper10] (categorized by subtopic)
  • §3 Method: [paper11] (baseline), [paper12] (technique we build on)

**Citation rules** (from claude-scholar + Imbad0202/academic-research-skills):
1. NEVER generate BibTeX from memory — always verify via search or existing .bib files
2. Every citation must be verified: correct authors, year, venue
3. Flag any citation you're unsure about with `[VERIFY]`
4. Prefer published versions over arXiv preprints when available
  • §1 引言：[文献1]、[文献2]、[文献3]（问题动机类）
  • §2 相关工作：[文献4]-[文献10]（按子主题分类）
  • §3 方法：[文献11]（基线方法）、[文献12]（本文基于的技术）

**引用规则**（来自claude-scholar + Imbad0202/academic-research-skills）：
1. **严禁凭记忆生成BibTeX** — 必须通过搜索或现有.bib文件验证
2. 所有引用必须验证：作者、年份、会议信息正确
3. 对不确定的引用标记`[VERIFY]`
4. 优先引用已发表版本，而非arXiv预印本

Step 6: Cross-Review with REVIEWER_MODEL

步骤6：通过REVIEWER_MODEL交叉评审

Send the complete outline to GPT-5.4 xhigh for feedback:
mcp__codex__codex:
  model: gpt-5.4
  config: {"model_reasoning_effort": "xhigh"}
  prompt: |
    Review this paper outline for a [VENUE] submission.
    [full outline including Claims-Evidence Matrix]

    Score 1-10 on:
    1. Logical flow — does the story build naturally?
    2. Claim-evidence alignment — every claim backed?
    3. Missing experiments or analysis
    4. Positioning relative to prior work
    5. Page budget feasibility (MAX_PAGES = main body to Conclusion end, excluding refs/appendix)

    For each weakness, suggest the MINIMUM fix.
    Be specific and actionable — "add X" not "consider more experiments".
Apply feedback before finalizing.
将完整大纲发送至GPT-5.4 xhigh获取反馈：
mcp__codex__codex:
  model: gpt-5.4
  config: {"model_reasoning_effort": "xhigh"}
  prompt: |
    Review this paper outline for a [VENUE] submission.
    [full outline including Claims-Evidence Matrix]

    Score 1-10 on:
    1. Logical flow — does the story build naturally?
    2. Claim-evidence alignment — every claim backed?
    3. Missing experiments or analysis
    4. Positioning relative to prior work
    5. Page budget feasibility (MAX_PAGES = main body to Conclusion end, excluding refs/appendix)

    For each weakness, suggest the MINIMUM fix.
    Be specific and actionable — "add X" not "consider more experiments".
应用反馈后再最终确定大纲。

Step 7: Output

步骤7：输出结果

Save the final outline to 
PAPER_PLAN.md
in the project root:
markdown
undefined
将最终大纲保存至项目根目录的
PAPER_PLAN.md
文件：
markdown
undefined

Paper Plan

论文规划

Title: [working title] Venue: [target venue] Type: [empirical/theory/method] Date: [today] Page budget: [MAX_PAGES] pages (main body to Conclusion end, excluding references & appendix) Section count: [N] (must match the number of section files that will be created)
标题：[暂定标题] 目标会议：[目标会议名称] 论文类型：[实证/理论/方法] 日期：[当前日期] 页数限制：[MAX_PAGES]页（正文从第一页到结论部分末尾，不含参考文献和附录） 章节数量：[N]（必须与后续要创建的章节文件数量一致）

Claims-Evidence Matrix

论点-证据矩阵

[from Step 1]
[来自步骤1的内容]

Structure

论文结构

[from Step 2-3, section by section]
[来自步骤2-3的分章节内容]

Figure Plan

图表规划

[from Step 4, with detailed hero figure description]
[来自步骤4的内容，含核心图的详细描述]

Citation Plan

引用规划

[from Step 5]
[来自步骤5的内容]

Reviewer Feedback

评审反馈

[from Step 6, summarized]
[来自步骤6的总结内容]

Next Steps

下一步行动

  • /paper-figure to generate all figures
  • /paper-write to draft LaTeX
  • /paper-compile to build PDF
undefined
  • /paper-figure 生成所有图表
  • /paper-write 撰写LaTeX初稿
  • /paper-compile 生成PDF文件
undefined

Key Rules

核心规则

  • Large file handling: If the Write tool fails due to file size, immediately retry using Bash (
    cat << 'EOF' > file
    ) to write in chunks. Do NOT ask the user for permission — just do it silently.
  • Do NOT generate author information — leave author block as placeholder or anonymous
  • Be honest about evidence gaps — mark claims as "needs experiment" rather than overclaiming
  • Page budget is hard — if content exceeds MAX_PAGES, suggest what to move to appendix
  • MAX_PAGES counts main body only — from first page to end of Conclusion. References and appendix are NOT counted.
  • Venue-specific norms — all three venues (ICLR/NeurIPS/ICML) use 
    natbib
    (
    \citep
    /
    \citet
    )
  • Claims-Evidence Matrix is the backbone — every claim must map to evidence, every experiment must support a claim
  • Figures need detailed descriptions — especially the hero figure, which must clearly specify comparisons and visual expectations
  • Section count is flexible — 5-8 sections depending on paper type. Don't force content into a rigid 5-section template.
  • 大文件处理：若Write工具因文件大小失败，立即通过Bash命令（
    cat << 'EOF' > file
    ）分块重试，无需询问用户许可 — 直接静默执行。
  • 严禁生成作者信息 — 作者区块留空或使用匿名占位符
  • 诚实披露证据缺口 — 将论点标记为“需补充实验”，而非夸大其词
  • 页数限制为硬约束 — 若内容超出MAX_PAGES，建议将部分内容移至附录
  • MAX_PAGES仅计算正文 — 从第一页到结论部分末尾，参考文献和附录不计入
  • 遵循会议特定规范 — 三个目标会议（ICLR/NeurIPS/ICML）均使用
    natbib
    （
    \citep
    /
    \citet
    ）
  • 论点-证据矩阵是核心 — 每个论点必须对应证据，每个实验必须支撑一个论点
  • 图表需详细描述 — 尤其是核心图，必须明确指定对比内容和视觉要求
  • 章节数量可灵活调整 — 根据论文类型设置5-8个章节，不要将内容强行塞入僵化的5章节模板

Acknowledgements

致谢

Outline methodology inspired by Research-Paper-Writing-Skills (claim-evidence mapping), claude-scholar (citation verification), and Imbad0202/academic-research-skills (claim verification protocol).
本大纲方法论灵感来源于Research-Paper-Writing-Skills（论点-证据映射）、claude-scholar（引用验证）和Imbad0202/academic-research-skills（论点验证流程）。