academic-paper
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAcademic Paper — Academic Paper Writing Agent Team
学术论文写作工具——12-Agent协作团队
A general-purpose academic paper writing tool — 12-agent pipeline covering all disciplines, with higher education domain as the default reference. v2.4 hardens LaTeX output formatting: mandatory document class for APA 7.0, text justification override for mode, table column width formula with deduction, bilingual abstract centering, standardized font stack (Times New Roman + Source Han Serif TC VF + Courier New), and PDF compilation via tectonic.
apa7man\tabcolsep一款通用学术论文写作工具——覆盖全学科的12-Agent流水线,默认以高等教育领域为参考场景。v2.4版本强化了LaTeX输出格式:针对APA 7.0格式强制使用文档类,修复模式下的文本对齐问题,新增包含扣除的表格列宽计算公式,实现双语摘要居中,标准化字体栈(Times New Roman + Source Han Serif TC VF + Courier New),并通过tectonic编译生成PDF。
apa7man\tabcolsepQuick Start
快速开始
Minimal command:
Write a paper on the impact of AI on higher education quality assuranceWrite a paper on the impact of declining birth rates on private university management strategiesExecution flow:
- Configuration interview — paper type, discipline, citation format, output format
- Literature search — systematic search strategy, source screening
- Architecture design — paper structure, outline, word count allocation
- Argumentation construction — claim-evidence chains, logical flow
- Full-text drafting — section-by-section draft, register adjustment
- Citation compliance + bilingual abstract (parallel)
- Peer review — five-dimension scoring, revision suggestions
- Output formatting — LaTeX/DOCX/PDF/Markdown
最简命令:
Write a paper on the impact of AI on higher education quality assuranceWrite a paper on the impact of declining birth rates on private university management strategies执行流程:
- 配置访谈——确定论文类型、学科、引用格式、输出格式
- 文献检索——制定系统检索策略、筛选文献来源
- 架构设计——确定论文结构、大纲、字数分配
- 论点构建——搭建主张-证据链、梳理逻辑脉络
- 全文撰写——分章节撰写草稿、调整学术语气
- 引用合规性检查 + 双语摘要撰写(并行)
- 同行评审——五维度评分、提供修订建议
- 格式输出——转换为LaTeX/DOCX/PDF/Markdown格式
Trigger Conditions
触发条件
Trigger Keywords
触发关键词
English: write paper, academic paper, paper outline, write abstract, revise paper, literature review paper, check citations, convert to LaTeX, convert format, format paper, conference paper, journal article, thesis chapter, research paper, guide my paper, help me plan my paper, step by step paper, draft manuscript, write methodology, write discussion, parse reviews, revision roadmap, help me with my revision, I got reviewer comments, convert citations
繁體中文: 寫論文, 學術論文, 論文大綱, 寫摘要, 修改論文, 文獻回顧論文, 檢查引用, 轉 LaTeX, 轉換格式, 研討會論文, 期刊文章, 學位論文, 研究論文, 引導我寫論文, 幫我規劃論文, 逐步寫論文, 寫方法論, 寫討論, 審查意見, 修訂路線圖, 幫我修改, 我收到審查意見, 轉換引用格式
英文:write paper, academic paper, paper outline, write abstract, revise paper, literature review paper, check citations, convert to LaTeX, convert format, format paper, conference paper, journal article, thesis chapter, research paper, guide my paper, help me plan my paper, step by step paper, draft manuscript, write methodology, write discussion, parse reviews, revision roadmap, help me with my revision, I got reviewer comments, convert citations
繁体中文:寫論文, 學術論文, 論文大綱, 寫摘要, 修改論文, 文獻回顧論文, 檢查引用, 轉 LaTeX, 轉換格式, 研討會論文, 期刊文章, 學位論文, 研究論文, 引導我寫論文, 幫我規劃論文, 逐步寫論文, 寫方法論, 寫討論, 審查意見, 修訂路線圖, 幫我修改, 我收到審查意見, 轉換引用格式
Plan Mode Activation
规划模式激活
Activate mode (Socratic chapter-by-chapter guidance) when the user's intent matches any of the following patterns, regardless of language. Detect meaning, not exact keywords.
planIntent signals (any one is sufficient):
- User wants to be guided or led through paper writing, not just given a finished paper
- User asks for step-by-step or chapter-by-chapter planning
- User expresses uncertainty about how to start or structure a paper
- User is a first-time paper writer or explicitly says they are a beginner
- User has research results but doesn't know how to turn them into a paper
- User wants to think through each section before writing
Default rule: When intent is ambiguous between and , prefer — it is safer to guide a user who needs help than to produce a paper they can't use. The user can always switch to later.
planfullplanfullExample triggers (illustrative, not exhaustive):
"guide my paper", "help me plan my paper", "I don't know how to start", 「引導我寫論文」「幫我規劃論文」, or equivalent in any language
当用户的意图匹配以下任意模式时,激活模式(苏格拉底式逐章引导),不受语言限制。需识别语义,而非精确关键词。
plan意图信号(满足其一即可):
- 用户希望获得论文写作引导,而非直接生成成品论文
- 用户要求分步或逐章规划论文
- 用户表示不确定如何开始或构建论文结构
- 用户是首次撰写论文或明确说明自己是新手
- 用户已有研究成果,但不知道如何转化为论文
- 用户希望在写作前梳理每个章节的内容
默认规则:当意图在和模式间模糊时,优先选择模式——为需要帮助的用户提供引导比生成他们无法使用的论文更稳妥。用户之后可随时切换到模式。
planfullplanfull触发示例(仅作说明,非穷尽):
"guide my paper", "help me plan my paper", "I don't know how to start", 「引導我寫論文」「幫我規劃論文」,或其他语言的等效表达
Does NOT Trigger
不触发场景
| Scenario | Use Instead |
|---|---|
| Deep research / fact-checking (not paper writing) | |
| Reviewing a paper (structured review) | |
| Full research-to-paper pipeline | |
| 场景 | 替代工具 |
|---|---|
| 深度研究/事实核查(非论文写作) | |
| 论文结构化评审 | |
| 从研究到论文的完整流水线 | |
Distinction from deep-research
deep-research与deep-research
的区别
deep-research| Feature | | |
|---|---|---|
| Primary output | Publishable paper draft | Research report |
| Structure | Journal-ready (IMRaD, etc.) | APA 7.0 report |
| Citation | Multi-format (APA/Chicago/MLA/IEEE/Vancouver) | APA 7.0 only |
| Abstract | Bilingual (zh-TW + EN) | Single language |
| Peer review | Simulated 5-dimension review | Editorial review |
| Output format | LaTeX/DOCX/PDF/Markdown | Markdown only |
| Revision loop | Max 2 rounds with targeted feedback | Max 2 rounds |
| 特性 | | |
|---|---|---|
| 主要输出 | 可投稿的论文草稿 | 研究报告 |
| 结构 | 符合期刊要求(IMRaD等) | APA 7.0格式报告 |
| 引用格式 | 多格式支持(APA/Chicago/MLA/IEEE/Vancouver) | 仅支持APA 7.0 |
| 摘要 | 双语(繁体中文+英文) | 单语言 |
| 同行评审 | 模拟五维度评审 | 编辑评审 |
| 输出格式 | LaTeX/DOCX/PDF/Markdown | 仅Markdown |
| 修订循环 | 最多2轮针对性反馈 | 最多2轮 |
Agent Team (12 Agents)
Agent团队(12个Agent)
| # | Agent | Role | Phase |
|---|---|---|---|
| 1 | | Configuration interview: paper type, discipline, journal, citation format, output format, language, word count; Handoff detection; Plan mode simplified interview | Phase 0 |
| 2 | | Search strategy design, source screening, annotated bibliography, literature matrix | Phase 1 |
| 3 | | Paper structure selection, detailed outline, word count allocation, evidence mapping | Phase 2 |
| 4 | | Argument construction, claim-evidence chains, logical flow, counter-argument handling; Plan mode argument stress test | Phase 3 / Plan Step 3 |
| 5 | | Section-by-section full draft writing, discipline register adjustment, word count tracking | Phase 4 |
| 6 | | Citation format verification, reference list completeness, DOI checking | Phase 5a |
| 7 | | Bilingual abstract (zh-TW + EN), 5-7 keywords each | Phase 5b |
| 8 | | Simulated double-blind review, five-dimension scoring, revision suggestions (max 2 rounds) | Phase 6 |
| 9 | | Convert to LaTeX/DOCX/PDF/Markdown, journal formatting, cover letter, citation format conversion (APA 7 / Chicago / MLA / IEEE / Vancouver) | Phase 7 |
| 10 | | Plan mode Socratic mentor: chapter-by-chapter guidance, convergence criteria (4 signals), question taxonomy (4 types), INSIGHT extraction | Plan Step 0-3 |
| 11 | | Parse paper data and generate publication-quality figure code (Python matplotlib / R ggplot2) with APA 7.0 formatting, colorblind-safe palettes, and LaTeX integration | Phase 4 / Phase 7 |
| 12 | | Parse unstructured reviewer comments into structured Revision Roadmap; classify, map, and prioritize comments; works standalone without prior pipeline execution | Revision-Coach mode |
| 序号 | Agent | 职责 | 阶段 |
|---|---|---|---|
| 1 | | 配置访谈:确定论文类型、学科、期刊、引用格式、输出格式、语言、字数;交接检测;规划模式简化访谈 | 阶段0 |
| 2 | | 制定检索策略、筛选文献来源、带注释的参考文献、文献矩阵 | 阶段1 |
| 3 | | 选择论文结构、制定详细大纲、分配字数、匹配证据 | 阶段2 |
| 4 | | 构建论点、搭建主张-证据链、梳理逻辑、处理反论点;规划模式下的论点压力测试 | 阶段3 / 规划步骤3 |
| 5 | | 分章节撰写完整草稿、调整学科语气、跟踪字数 | 阶段4 |
| 6 | | 验证引用格式、检查参考文献完整性、DOI校验 | 阶段5a |
| 7 | | 撰写双语摘要(繁体中文+英文)、各语言5-7个关键词 | 阶段5b |
| 8 | | 模拟双盲评审、五维度评分、提供修订建议(最多2轮) | 阶段6 |
| 9 | | 转换为LaTeX/DOCX/PDF/Markdown格式、期刊格式调整、附信、引用格式转换(APA 7 / Chicago / MLA / IEEE / Vancouver) | 阶段7 |
| 10 | | 规划模式下的苏格拉底式导师:逐章引导、收敛标准(4个信号)、问题分类(4种类型)、提取INSIGHT | 规划步骤0-3 |
| 11 | | 解析论文数据,生成符合出版标准的图表代码(Python matplotlib / R ggplot2),支持APA 7.0格式、色盲友好调色板及LaTeX集成 | 阶段4 / 阶段7 |
| 12 | | 将非结构化评审意见解析为结构化修订路线图;分类、映射并优先处理意见;无需执行完整流水线即可独立运行 | 修订导师模式 |
Output Formats
输出格式
Text Formats
文本格式
LaTeX (.tex + .bib), DOCX (via Pandoc), PDF (via LaTeX or Pandoc), Markdown.
LaTeX(.tex + .bib)、DOCX(通过Pandoc)、PDF(通过LaTeX或Pandoc)、Markdown。
Figures
图表
When the paper contains quantitative results, the can generate publication-ready figures in Python (matplotlib/seaborn) or R (ggplot2) with APA 7.0 formatting and colorblind-safe palettes. Figures are delivered as runnable code + LaTeX integration code. See for chart type decision trees and code templates.
visualization_agent\includegraphicsreferences/statistical_visualization_standards.md当论文包含量化结果时,可生成符合出版标准的Python(matplotlib/seaborn)或R(ggplot2)图表代码,支持APA 7.0格式和色盲友好调色板。图表以可运行代码+LaTeX 集成代码的形式交付。图表类型决策树和代码模板详见。
visualization_agent\includegraphicsreferences/statistical_visualization_standards.mdCitation Formats
引用格式
APA 7.0 (default), Chicago (Author-Date or Notes-Bibliography), MLA 9, IEEE, Vancouver. The supports late-stage citation format conversion between any two supported formats via "Convert citations to [format]".
formatter_agentAPA 7.0(默认)、Chicago(作者-日期或注释-参考文献)、MLA 9、IEEE、Vancouver。支持通过“Convert citations to [format]”指令在任意两种支持格式间进行后期引用格式转换。
formatter_agentOrchestration Workflow (8 Phases)
编排工作流(8个阶段)
User: "Write a paper on [topic]"
|
=== Phase 0: CONFIG (Interactive) ===
|
+-> [intake_agent] -> Paper Configuration Record
- Paper type (IMRaD / Lit Review / Theoretical / Case Study / Policy Brief / Conference)
- Discipline and sub-field
- Target journal (optional)
- Citation format (APA 7 / Chicago / MLA / IEEE / Vancouver)
- Output format (LaTeX / DOCX / PDF / Markdown / Combined)
- Language (EN / zh-TW / bilingual sections)
- Bilingual abstract (Yes / EN-only / zh-TW-only)
- Word count target
- Existing materials (RQ, data, drafts, lit)
|
** User confirms configuration **
|
=== Phase 1: RESEARCH ===
|
+-> [literature_strategist_agent] -> Search Strategy + Source Corpus
- Database selection + search strings
- Inclusion/exclusion criteria
- Source screening + annotated bibliography
- Literature matrix (Source x Theme)
- Research gap mapping
|
** User reviews sources (optional add/remove) **
|
=== Phase 2: ARCHITECTURE ===
|
+-> [structure_architect_agent] -> Paper Outline + Evidence Map
- Structure pattern selection (from paper_structure_patterns.md)
- Section-by-section outline with word count allocation
- Evidence-to-section assignment
- Transition logic between sections
|
** User approves outline **
|
=== Phase 3: ARGUMENTATION ===
|
+-> [argument_builder_agent] -> Argument Blueprint
- Central thesis + sub-arguments
- Claim-Evidence-Reasoning chains per section
- Counter-argument identification + rebuttal strategy
- Logical flow diagram
|
=== Phase 4: DRAFTING ===
|
+-> [draft_writer_agent] -> Complete Draft
- Section-by-section writing following outline
- Register adjustment for discipline
- In-text citations integrated
- Word count tracking per section
- Transition paragraphs between sections
|
=== Phase 5a & 5b: CITATIONS + ABSTRACT (Parallel) ===
|
|-> [citation_compliance_agent] -> Citation Audit Report
| - In-text <-> reference list cross-check (zero orphans)
| - Format compliance (per selected style)
| - DOI/URL verification
| - Self-citation ratio check
| - Auto-correction of detected errors
|
+-> [abstract_bilingual_agent] -> Bilingual Abstract + Keywords
- English abstract (150-300 words, structured)
- Traditional Chinese abstract (300-500 characters, structured)
- EN keywords (5-7)
- zh-TW keywords (5-7)
- Independent writing (not mechanical translation)
|
=== Phase 6: PEER REVIEW ===
|
+-> [peer_reviewer_agent] -> Review Report + Revision Instructions
- 5-dimension scoring:
Originality (20%) | Methodological Rigor (25%) | Evidence Sufficiency (25%)
Argument Coherence (15%) | Writing Quality (15%)
- Verdict: Accept / Minor Revision / Major Revision / Reject
- Line-level feedback with suggested fixes
- Max 2 revision loops -> back to Phase 4 [draft_writer_agent] (limited to 1 round in academic-pipeline)
|
=== Phase 7: FORMAT ===
|
+-> [formatter_agent] -> Final Output Package
- Target format conversion (LaTeX + .bib / DOCX / PDF / Markdown)
- Journal-specific formatting (if target journal specified)
- Cover letter (if journal submission)
- AI disclosure statement
- Final quality checklist用户:"Write a paper on [topic]"
|
=== 阶段0:配置(交互式) ===
|
+-> [intake_agent] -> 论文配置记录
- 论文类型(IMRaD / 文献综述 / 理论研究 / 案例研究 / 政策简报 / 会议论文)
- 学科及子领域
- 目标期刊(可选)
- 引用格式(APA 7 / Chicago / MLA / IEEE / Vancouver)
- 输出格式(LaTeX / DOCX / PDF / Markdown / 组合格式)
- 语言(英文 / 繁体中文 / 双语章节)
- 双语摘要(是 / 仅英文 / 仅繁体中文)
- 目标字数
- 已有材料(研究问题、数据、草稿、文献)
|
** 用户确认配置 **
|
=== 阶段1:研究 ===
|
+-> [literature_strategist_agent] -> 检索策略 + 文献库
- 数据库选择 + 检索字符串
- 纳入/排除标准
- 文献筛选 + 带注释的参考文献
- 文献矩阵(来源×主题)
- 研究缺口映射
|
** 用户审核文献(可选添加/移除) **
|
=== 阶段2:架构 ===
|
+-> [structure_architect_agent] -> 论文大纲 + 证据映射
- 从paper_structure_patterns.md中选择结构模式
- 分章节大纲及字数分配
- 证据与章节的匹配
- 章节间的过渡逻辑
|
** 用户批准大纲 **
|
=== 阶段3:论点构建 ===
|
+-> [argument_builder_agent] -> 论点蓝图
- 核心论点 + 子论点
- 各章节的主张-证据-推理链
- 反论点识别 + 反驳策略
- 逻辑流程图
|
=== 阶段4:撰写 ===
|
+-> [draft_writer_agent] -> 完整草稿
- 按照大纲分章节撰写
- 调整学科学术语气
- 集成文内引用
- 跟踪各章节字数
- 章节间的过渡段落
|
=== 阶段5a & 5b:引用检查 + 摘要撰写(并行) ===
|
|-> [citation_compliance_agent] -> 引用审核报告
| - 文内引用与参考文献列表交叉校验(无孤立引用)
| - 格式合规性(符合所选风格)
| - DOI/URL验证
| - 自引率检查
| - 自动修正检测到的错误
|
+-> [abstract_bilingual_agent] -> 双语摘要 + 关键词
- 英文摘要(150-300词,结构化)
- 繁体中文摘要(300-500字,结构化)
- 英文关键词(5-7个)
- 繁体中文关键词(5-7个)
- 独立撰写(非机器翻译)
|
=== 阶段6:同行评审 ===
|
+-> [peer_reviewer_agent] -> 评审报告 + 修订说明
- 五维度评分:
原创性(20%)| 方法严谨性(25%)| 证据充分性(25%)
论点连贯性(15%)| 写作质量(15%)
- 结论:接受 / 小修 / 大修 / 拒稿
- 行级反馈及修复建议
- 最多2轮修订循环 -> 返回阶段4 [draft_writer_agent](在academic-pipeline中限制为1轮)
|
=== 阶段7:格式输出 ===
|
+-> [formatter_agent] -> 最终输出包
- 目标格式转换(LaTeX + .bib / DOCX / PDF / Markdown)
- 期刊特定格式调整(若指定目标期刊)
- 投稿附信(若用于期刊投稿)
- AI披露声明
- 最终质量检查表Checkpoint Rules
检查点规则
- Phase 0 -> 1: User must confirm Paper Configuration Record
- Phase 2 -> 3: User must approve outline (can request restructuring)
- Phase 6: Max 2 revision loops; unresolved items -> "Acknowledged Limitations"
- Peer Review Critical-severity issues block progression to Phase 7
- User can skip Phase 1 (literature) if providing own sources
- 阶段0 -> 1:用户必须确认论文配置记录
- 阶段2 -> 3:用户必须批准大纲(可要求调整结构)
- 阶段6:最多2轮修订循环;未解决项归入“已确认局限性”
- 同行评审:严重问题会阻止进入阶段7
- 用户若提供自有文献,可跳过阶段1(文献检索)
Operational Modes (9 Modes)
运行模式(9种模式)
See for details.
references/mode_selection_guide.md| Mode | Trigger | Agents | Output |
|---|---|---|---|
| "Write a paper" | All 9 (+ 11 if quantitative) | Complete paper draft (with figures if applicable) |
| "Paper outline" | 1->2->3 | Detailed outline + evidence map |
| "Revise paper" | 8->5->6 | Revised draft with tracked changes (uses |
| "Write abstract" | 1->7 | Bilingual abstract + keywords |
| "Literature review" | 1->2 | Annotated bibliography + synthesis |
| "Convert to LaTeX" / "Convert citations to [format]" | 9 only | Formatted document; includes citation format conversion (APA 7 / Chicago / MLA / IEEE / Vancouver) |
| "Check citations" | 6 only | Citation error report |
| "guide my paper" / "help me plan my paper" | 1->10->3->4 | Chapter Plan + INSIGHT Collection |
| "parse reviews" / "revision roadmap" / "I got reviewer comments" | 12 only | Revision Roadmap + optional Tracking Template + Response Letter Skeleton |
详情请见。
references/mode_selection_guide.md| 模式 | 触发词 | 涉及Agent | 输出 |
|---|---|---|---|
| "Write a paper" | 全部9个(若含量化内容则加第11个) | 完整论文草稿(如需则包含图表) |
| "Paper outline" | 1->2->3 | 详细大纲 + 证据映射 |
| "Revise paper" | 8->5->6 | 带修订跟踪的草稿(使用 |
| "Write abstract" | 1->7 | 双语摘要 + 关键词 |
| "Literature review" | 1->2 | 带注释的参考文献 + 文献综述 |
| "Convert to LaTeX" / "Convert citations to [format]" | 仅第9个 | 格式化文档;包含引用格式转换(APA 7 / Chicago / MLA / IEEE / Vancouver) |
| "Check citations" | 仅第6个 | 引用错误报告 |
| "guide my paper" / "help me plan my paper" | 1->10->3->4 | 章节规划 + INSIGHT集合 |
| "parse reviews" / "revision roadmap" / "I got reviewer comments" | 仅第12个 | 修订路线图 + 可选跟踪模板 + 回复信框架 |
Quick Mode Selection Guide
快速模式选择指南
| Your Situation | Recommended Mode |
|---|---|
| Starting from scratch with a clear RQ | |
| Need help planning before writing | |
| Just need an outline | |
| Have a draft, received review feedback | |
| Have unstructured reviewer comments | |
| Just need an abstract | |
| Need to check/fix citations | |
| Need to convert format (LaTeX, DOCX) or citation style | |
| Want a systematic literature review paper | |
Not sure? Start with — it will guide you step by step.
plan| 你的场景 | 推荐模式 |
|---|---|
| 从零开始,研究问题明确 | |
| 写作前需要规划帮助 | |
| 仅需要论文大纲 | |
| 已有草稿,收到评审反馈 | |
| 有非结构化评审意见 | |
| 仅需要摘要 | |
| 需要检查/修复引用 | |
| 需要转换格式(LaTeX、DOCX)或引用风格 | |
| 需要系统的文献综述论文 | |
不确定选什么?从模式开始——它会逐步引导你。
planMode Selection Logic
模式选择逻辑
"Write a paper on SDGs in HEI" -> full
"Give me a paper outline for..." -> outline-only
"Revise this paper based on feedback" -> revision
"Write an abstract for this paper" -> abstract-only
"Do a literature review on..." -> lit-review
"Convert this paper to LaTeX" -> format-convert
"Convert citations to IEEE" -> format-convert
"Check the citations in this paper" -> citation-check
"guide my paper" -> plan
"help me plan my paper" -> plan
"I got reviewer comments" -> revision-coach
"parse these reviews" -> revision-coach
"help me with my revision" -> revision-coach"Write a paper on SDGs in HEI" -> full
"Give me a paper outline for..." -> outline-only
"Revise this paper based on feedback" -> revision
"Write an abstract for this paper" -> abstract-only
"Do a literature review on..." -> lit-review
"Convert this paper to LaTeX" -> format-convert
"Convert citations to IEEE" -> format-convert
"Check the citations in this paper" -> citation-check
"guide my paper" -> plan
"help me plan my paper" -> plan
"I got reviewer comments" -> revision-coach
"parse these reviews" -> revision-coach
"help me with my revision" -> revision-coachPlan Mode: CHAPTER-BY-CHAPTER GUIDED PLANNING
规划模式:逐章引导规划
Core principle: From the perspective of a senior doctoral advisor and disciplinary methodology expert, guide users to think through every part of their paper chapter by chapter. Instead of writing directly, use Socratic dialogue to help users clarify what they want to write.
User: "guide my paper" / "help me plan my paper"
|
=== Step 0: RESEARCH READINESS CHECK ===
|
+-> [socratic_mentor_agent] -> Confirm what materials the user already has
- "What research materials do you currently have? (literature, data, analysis results)"
- "Is your research question finalized? Can you state it in one sentence?"
-> If research foundation is lacking, recommend running deep-research (socratic mode) first
|
=== Step 1: THESIS CRYSTALLIZATION ===
|
+-> [socratic_mentor_agent] -> Probe the core thesis
- "What is your paper arguing?"
- "How would someone who disagrees with you respond?"
- "After reading your paper, what should the reader think differently about?"
Extract [INSIGHT: thesis_statement]
|
=== Step 2: CHAPTER-BY-CHAPTER NEGOTIATION ===
|
For each chapter (Introduction -> Literature -> Method -> Results -> Discussion -> Conclusion):
|
+-> [socratic_mentor_agent] -> Probe the purpose and content of each chapter
|
| Introduction:
| - "What sense of urgency should the reader feel by the end of this chapter?"
| - "After reading the Introduction, what should the reader expect to see next?"
| - "What is your research gap? State it in one sentence."
|
| Literature Review:
| - "How many stories are you telling? What is the relationship between them?"
| - "What conclusion should your literature review ultimately lead to?"
| - "Is there an important work you disagree with? Why?"
|
| Methodology:
| - "If someone challenges your method, how would you respond?"
| - "Is there a simpler method that could also answer your question? Why didn't you choose it?"
| - "What is the biggest limitation of your method? How do you handle it?"
|
| Results:
| - "What is your most important finding? State it in one sentence."
| - "Were there any unexpected results? How do you explain them?"
| - "Is there any evidence in your data that does not support your hypothesis?"
|
| Discussion:
| - "How do your results dialogue with existing literature?"
| - "What is the one thing you most want the reader to remember?"
| - "What recommendations does your research have for practice/policy?"
|
| Conclusion:
| - "If you could only leave one paragraph, what would you say?"
| - "What future research directions does your study open up?"
|
At least 2 rounds of dialogue per chapter
After each chapter concludes, [socratic_mentor_agent] extracts a Chapter Summary
|
+-> [structure_architect_agent] -> Produce complete outline based on all Chapter Summaries
|
=== Step 3: ARGUMENT STRESS TEST ===
|
+-> [socratic_mentor_agent + argument_builder_agent]
-> Probe evidence and logic for each sub-argument
-> "Where is the weakest point in this argument?"
-> "If you reverse your argument, does it still hold?"
-> Final output: Chapter Plan (with core argument, supporting evidence, expected word count per chapter)
|
Output: Chapter Plan + INSIGHT Collection
-> User can then use full mode to produce the complete paper
-> Or use academic-paper-reviewer to review the Chapter Plan核心原则:以资深博导和学科方法论专家的视角,引导用户逐章思考论文的每个部分。不直接撰写,而是通过苏格拉底式对话帮助用户明确写作内容。
用户:"guide my paper" / "help me plan my paper"
|
=== 步骤0:研究准备情况检查 ===
|
+-> [socratic_mentor_agent] -> 确认用户已有的材料
- "你目前拥有哪些研究材料?(文献、数据、分析结果)"
- "你的研究问题是否已确定?能否用一句话表述?"
-> 若研究基础不足,建议先运行deep-research(苏格拉底模式)
|
=== 步骤1:论点明确 ===
|
+-> [socratic_mentor_agent] -> 探究核心论点
- "你的论文要论证什么?"
- "持反对意见的人会如何回应?"
- "读者读完你的论文后,应该在哪些观点上产生转变?"
提取[INSIGHT: thesis_statement]
|
=== 步骤2:逐章协商 ===
|
针对每个章节(引言 -> 文献综述 -> 研究方法 -> 研究结果 -> 讨论 -> 结论):
|
+-> [socratic_mentor_agent] -> 探究各章节的目的和内容
|
| 引言:
| - "读者读完本章后应感受到怎样的紧迫性?"
| - "读完引言后,读者接下来预期看到什么内容?"
| - "你的研究缺口是什么?用一句话表述。"
|
| 文献综述:
| - "你要讲述几个研究脉络?它们之间的关系是什么?"
| - "你的文献综述最终要得出什么结论?"
| - "是否有你不同意的重要研究?原因是什么?"
|
| 研究方法:
| - "若有人质疑你的方法,你会如何回应?"
| - "是否有更简单的方法也能回答你的研究问题?你为何不选择它?"
| - "你的方法最大的局限性是什么?你如何处理?"
|
| 研究结果:
| - "你最重要的发现是什么?用一句话表述。"
| - "是否有意外结果?你如何解释?"
| - "你的数据中是否有不支持假设的证据?"
|
| 讨论:
| - "你的研究结果如何与现有文献对话?"
| - "你最希望读者记住哪一点?"
| - "你的研究对实践/政策有哪些建议?"
|
| 结论:
| - "若只能留下一个段落,你会写什么?"
| - "你的研究为未来研究开辟了哪些方向?"
|
每章至少进行2轮对话
每章结束后,[socratic_mentor_agent]提取章节摘要
|
+-> [structure_architect_agent] -> 根据所有章节摘要生成完整大纲
|
=== 步骤3:论点压力测试 ===
|
+-> [socratic_mentor_agent + argument_builder_agent]
-> 探究每个子论点的证据和逻辑
-> "这个论点最薄弱的环节在哪里?"
-> "若反转你的论点,是否仍然成立?"
-> 最终输出:章节规划(包含核心论点、支持证据、各章节预期字数)
|
输出:章节规划 + INSIGHT集合
-> 用户随后可使用full模式生成完整论文
-> 或使用academic-paper-reviewer评审章节规划Handoff Protocol: deep-research -> academic-paper
交接协议:deep-research -> academic-paper
intake_agentdeep-research/SKILL.mdintake_agentdeep-research/SKILL.mdFailure Paths
失败路径
See for details. Quick reference:
references/failure_paths.md| Failure Scenario | Handling Strategy |
|---|---|
| Insufficient research foundation | Recommend running |
| Wrong paper structure selected | Return to Phase 2, suggest alternative structure |
| Word count significantly over/under target | Identify problematic chapters, suggest trimming/expansion |
| Citation format entirely wrong | Re-run the entire citation phase |
| Peer review rejection | Analyze rejection reasons, suggest major revision or restructuring |
| Plan mode not converging | Suggest switching to outline-only mode |
| Incomplete handoff materials | List missing items, suggest supplementing or re-running |
| User abandons midway | Save completed Chapter Plan |
详情请见。快速参考:
references/failure_paths.md| 失败场景 | 处理策略 |
|---|---|
| 研究基础不足 | 建议先运行 |
| 论文结构选择错误 | 返回阶段2,建议替代结构 |
| 字数显著超出/低于目标 | 识别问题章节,建议删减/扩充 |
| 引用格式完全错误 | 重新运行整个引用检查阶段 |
| 同行评审拒稿 | 分析拒稿原因,建议大修或调整结构 |
| 规划模式无法收敛 | 建议切换到outline-only模式 |
| 交接材料不完整 | 列出缺失项,建议补充或重新运行 |
| 用户中途放弃 | 保存已完成的章节规划 |
Full Academic Pipeline
完整学术流水线
See for the complete workflow.
academic-pipeline/SKILL.md完整工作流详见。
academic-pipeline/SKILL.mdPhase 0: Configuration Interview
阶段0:配置访谈
See for the complete field definitions of the Phase 0 configuration interview. The interview covers 9 items: paper type, discipline, target journal, citation format, output format, language, abstract, word count, and existing materials. Outputs a Paper Configuration Record, awaiting user confirmation.
agents/intake_agent.md阶段0配置访谈的完整字段定义详见。访谈涵盖9项内容:论文类型、学科、目标期刊、引用格式、输出格式、语言、摘要、字数、已有材料。输出论文配置记录,等待用户确认。
agents/intake_agent.mdAgent File References
Agent文件参考
| Agent | Definition File |
|---|---|
| intake_agent | |
| literature_strategist_agent | |
| structure_architect_agent | |
| argument_builder_agent | |
| draft_writer_agent | |
| citation_compliance_agent | |
| abstract_bilingual_agent | |
| peer_reviewer_agent | |
| formatter_agent | |
| socratic_mentor_agent | |
| visualization_agent | |
| revision_coach_agent | |
| Agent | 定义文件 |
|---|---|
| intake_agent | |
| literature_strategist_agent | |
| structure_architect_agent | |
| argument_builder_agent | |
| draft_writer_agent | |
| citation_compliance_agent | |
| abstract_bilingual_agent | |
| peer_reviewer_agent | |
| formatter_agent | |
| socratic_mentor_agent | |
| visualization_agent | |
| revision_coach_agent | |
Reference Files
参考文件
| Reference | Purpose | Used By |
|---|---|---|
| APA 7th extended guide (extends deep-research version) | citation_compliance, draft_writer, formatter |
| APA 7.0 Chinese citation complete specification (Taiwan academic conventions) | citation_compliance, draft_writer, formatter |
| Multi-citation format switching rules (including Chinese formats) | citation_compliance, formatter |
| 6 paper structure patterns | structure_architect, intake |
| Academic writing style guide | draft_writer, peer_reviewer |
| Higher education terminology bilingual glossary | all agents (domain context) |
| Journal submission guide | formatter, intake |
| Abstract writing guide | abstract_bilingual |
| LaTeX template reference | formatter |
| Failure path map (12 scenarios + handling strategies) | all agents |
| 8 mode selection guide + transition paths | intake |
| CRediT 14 roles + ICMJE + AI policy + contribution matrix | intake, formatter, draft_writer |
| Taiwan/international funding formats + statement templates | intake, formatter, draft_writer |
| APA 7.0 figure guidelines, accessible color palettes, chart type decision tree, matplotlib/ggplot2 code templates | visualization |
Also references from :
deep-research- — base APA 7 reference (this skill extends, not duplicates)
deep-research/references/apa7_style_guide.md
| 参考文件 | 用途 | 使用Agent |
|---|---|---|
| APA 7版扩展指南(基于deep-research版本扩展) | citation_compliance, draft_writer, formatter |
| APA 7.0中文引用完整规范(台湾学术惯例) | citation_compliance, draft_writer, formatter |
| 多引用格式转换规则(含中文格式) | citation_compliance, formatter |
| 6种论文结构模式 | structure_architect, intake |
| 学术写作风格指南 | draft_writer, peer_reviewer |
| 高等教育术语双语词汇表 | 所有Agent(领域上下文) |
| 期刊投稿指南 | formatter, intake |
| 摘要写作指南 | abstract_bilingual |
| LaTeX模板参考 | formatter |
| 失败路径映射(12种场景+处理策略) | 所有Agent |
| 8种模式选择指南+转换路径 | intake |
| CRediT 14种角色 + ICMJE + AI政策 + 贡献矩阵 | intake, formatter, draft_writer |
| 台湾/国际资助格式+声明模板 | intake, formatter, draft_writer |
| APA 7.0图表指南、无障碍调色板、图表类型决策树、matplotlib/ggplot2代码模板 | visualization |
同时参考中的文件:
deep-research- — APA 7基础参考(本工具在此基础上扩展,而非重复)
deep-research/references/apa7_style_guide.md
Templates
模板
| Template | Purpose |
|---|---|
| IMRaD structure template |
| Literature review template |
| Case study template |
| Theoretical paper template |
| Policy brief template |
| Conference paper template |
| LaTeX starter template |
| Bilingual abstract template |
| Author x Role contribution matrix + CRediT statement output |
| Funding source registration + statement output |
| Systematic tracker for reviewer comments and resolutions during revision (4 status types: RESOLVED, DELIBERATE_LIMITATION, UNRESOLVABLE, REVIEWER_DISAGREE) |
| 模板 | 用途 |
|---|---|
| IMRaD结构模板 |
| 文献综述模板 |
| 案例研究模板 |
| 理论研究论文模板 |
| 政策简报模板 |
| 会议论文模板 |
| LaTeX入门模板 |
| 双语摘要模板 |
| 作者×角色贡献矩阵 + CRediT声明输出 |
| 资助来源登记+声明输出 |
| 修订阶段评审意见及解决方案的系统跟踪表(4种状态类型:已解决、刻意保留的局限性、无法解决、评审意见分歧) |
Examples
示例
| Example | Demonstrates |
|---|---|
| Complete IMRaD paper example (higher education domain, English) |
| Literature review paper example |
| Plan mode chapter-by-chapter guided dialogue example (blended learning topic) |
| Complete Chinese academic paper example (IMRaD, Chinese APA 7.0 citations) |
| Revision mode complete workflow: peer review response + revision comparison table |
| 示例 | 展示内容 |
|---|---|
| 完整IMRaD论文示例(高等教育领域,英文) |
| 文献综述论文示例 |
| 规划模式下逐章引导对话示例(混合学习主题) |
| 完整中文学术论文示例(IMRaD结构,中文APA 7.0引用) |
| 修订模式完整工作流:同行评审回复+修订对比表 |
Quality Standards
质量标准
Writing Quality
写作质量
- Every claim must have a citation or be supported by the paper's own data
- Zero citation orphans — in-text citations <-> reference list must perfectly match
- Consistent register — academic tone appropriate for the discipline
- Logical flow — clear transitions between paragraphs and sections
- Word count compliance — within +/-10% of target
- 所有主张必须有引用支持或由论文自身数据支撑
- 无孤立引用——文内引用与参考文献列表必须完全匹配
- 语气一致——采用符合学科要求的学术语气
- 逻辑连贯——段落和章节间过渡清晰
- 字数合规——与目标字数偏差在±10%以内
Bilingual Abstract Quality
双语摘要质量
- Independent writing — zh-TW and EN abstracts are independently composed, NOT mechanical translations
- Structural alignment — both abstracts cover the same key points in the same order
- Keywords — 5-7 per language, reflecting the paper's core concepts
- Word count — EN: 150-300 words; zh-TW: 300-500 characters
- 独立撰写——繁体中文和英文摘要为独立创作,而非机器翻译
- 结构对齐——两种语言的摘要涵盖相同要点且顺序一致
- 关键词——每种语言5-7个,反映论文核心概念
- 字数要求——英文:150-300词;繁体中文:300-500字
Citation Quality
引用质量
- Format compliance — 100% adherence to selected citation style
- DOI inclusion — every source with a DOI must include it
- Currency — flag sources older than 10 years (unless seminal works)
- Self-citation ratio — flag if >15%
- 格式合规——100%符合所选引用风格
- 包含DOI——所有有DOI的来源必须包含该标识
- 时效性——标记10年以上的文献(经典文献除外)
- 自引率——若自引率>15%则标记
Peer Review
同行评审
- Five dimensions — Originality (20%), Methodological Rigor (25%), Evidence Sufficiency (25%), Argument Coherence (15%), Writing Quality (15%)
- Actionable feedback — every criticism must include a specific suggestion
- Max 2 revision rounds — unresolved items become Acknowledged Limitations
- 五维度评分——原创性(20%)、方法严谨性(25%)、证据充分性(25%)、论点连贯性(15%)、写作质量(15%)
- 可执行反馈——每条批评必须包含具体建议
- 最多2轮修订——未解决项归入“已确认局限性”
Mandatory Inclusions
强制包含内容
- AI disclosure statement — every paper must include a statement on AI tool usage
- Limitations section — explicitly discuss study limitations
- Ethics statement — when applicable (human subjects, sensitive data)
- AI披露声明——每篇论文必须包含AI工具使用声明
- 局限性章节——明确讨论研究局限性
- 伦理声明——适用时(涉及人类受试者、敏感数据)
Output Language
输出语言
Follows the user's language. Academic terminology is kept in English. Bilingual abstracts are always provided regardless of the main text language.
遵循用户使用的语言。学术术语保留英文。无论正文语言如何,均提供双语摘要。
Integration with Other Skills
与其他工具的集成
academic-paper + tw-hei-intelligence -> Evidence-based HEI paper with real MOE data
academic-paper + deep-research -> Deep research phase -> paper writing phase (auto-handoff)
academic-paper + report-to-website -> Interactive web version of the paper
academic-paper + notebooklm-slides-generator -> Presentation slides from paper
academic-paper + academic-paper-reviewer -> Peer review -> revision loopacademic-paper + tw-hei-intelligence -> 基于真实MOE数据的循证高等教育论文
academic-paper + deep-research -> 深度研究阶段 -> 论文写作阶段(自动交接)
academic-paper + report-to-website -> 论文的交互式网页版本
academic-paper + notebooklm-slides-generator -> 基于论文的演示幻灯片
academic-paper + academic-paper-reviewer -> 同行评审 -> 修订循环Version History
版本历史
| Version | Date | Changes |
|---|---|---|
| 2.4 | 2026-03-08 | LaTeX output formatting hardening: mandatory |
| 2.3 | 2026-03-08 | NEW visualization_agent (11th: publication-quality figures with matplotlib/ggplot2, APA 7.0, colorblind-safe); NEW revision_coach_agent (12th: standalone reviewer comment parser → Revision Roadmap); Socratic convergence criteria (4 signals: thesis clarity, chapter coherence, evidence mapping, limitation honesty) + question taxonomy (clarifying, probing, structuring, challenging); revision tracking template (4 status types); citation format conversion in formatter_agent (APA 7 ↔ Chicago ↔ MLA ↔ IEEE ↔ Vancouver); Quick Mode Selection Guide; 9th mode: revision-coach |
| 2.2 | 2025-03-05 | 4-level argument strength scoring with quantified thresholds; plagiarism & retraction screening protocol; F11 Desk-Reject Recovery + F12 Conference-to-Journal Conversion failure paths; Plan -> Full mode conversion protocol; cross-skill reference to |
| 2.1 | 2026-03 | Added CRediT authorship guide, funding statement guide, 2 new templates (credit_statement_template, funding_statement_template); enhanced intake_agent with co-author + funding questions (Step 9-10); enhanced formatter_agent with CRediT + funding quality checks |
| 2.0 | 2026-02 | NEW plan mode (Socratic guided chapter-by-chapter planning), deep-research handoff protocol, Chinese APA 7.0 citation guide, failure path handling, mode selection guide |
| 1.0 | 2026-01 | Initial release: 9-agent pipeline, 6 paper types, 5 citation formats, bilingual abstracts, multi-format output |
| 版本 | 日期 | 变更内容 |
|---|---|---|
| 2.4 | 2026-03-08 | 强化LaTeX输出格式:APA 7.0输出强制使用 |
| 2.3 | 2026-03-08 | 新增visualization_agent(第11个:生成符合出版标准的matplotlib/ggplot2图表,支持APA 7.0、色盲友好调色板);新增revision_coach_agent(第12个:独立解析评审意见→修订路线图);苏格拉底式收敛标准(4个信号:论点清晰度、章节连贯性、证据映射、局限性坦诚度)+问题分类(澄清、探究、结构化、挑战);修订跟踪模板(4种状态类型);formatter_agent支持引用格式转换(APA 7 ↔ Chicago ↔ MLA ↔ IEEE ↔ Vancouver);新增快速模式选择指南;新增第9种模式:revision-coach |
| 2.2 | 2025-03-05 | 4级论点强度评分及量化阈值;抄袭与撤稿筛查协议;F11 desk-reject恢复+F12会议论文转期刊论文失败路径;Plan→Full模式转换协议;跨工具引用 |
| 2.1 | 2026-03 | 新增CRediT作者指南、资助声明指南、2个新模板(credit_statement_template、funding_statement_template);intake_agent新增合著者+资助问题(步骤9-10);formatter_agent新增CRediT+资助质量检查 |
| 2.0 | 2026-02 | 新增plan模式(苏格拉底式逐章引导规划)、deep-research交接协议、中文APA 7.0引用指南、失败路径处理、模式选择指南 |
| 1.0 | 2026-01 | 初始版本:9-Agent流水线、6种论文类型、5种引用格式、双语摘要、多格式输出 |