Academic Paper — Academic Paper Writing Agent Team

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 apa7 document class for APA 7.0, text justification override for man mode, table column width formula with \tabcolsep deduction, bilingual abstract centering, standardized font stack (Times New Roman + Source Han Serif TC VF + Courier New), and PDF compilation via tectonic.

Quick Start

Minimal command:

Write a paper on the impact of AI on higher education quality assurance

Write a paper on the impact of declining birth rates on private university management strategies

Execution flow:

1. Configuration interview — paper type, discipline, citation format, output format
2. Literature search — systematic search strategy, source screening
3. Architecture design — paper structure, outline, word count allocation
4. Argumentation construction — claim-evidence chains, logical flow
5. Full-text drafting — section-by-section draft, register adjustment
6. Citation compliance + bilingual abstract (parallel)
7. Peer review — five-dimension scoring, revision suggestions
8. Output formatting — LaTeX/DOCX/PDF/Markdown

Trigger Conditions

Trigger Keywords

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

Plan Mode Activation

Activate plan 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.

Intent signals (any one is sufficient):

1. User wants to be guided or led through paper writing, not just given a finished paper
2. User asks for step-by-step or chapter-by-chapter planning
3. User expresses uncertainty about how to start or structure a paper
4. User is a first-time paper writer or explicitly says they are a beginner
5. User has research results but doesn't know how to turn them into a paper
6. User wants to think through each section before writing

Default rule: When intent is ambiguous between plan and full, prefer plan — 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 full later.

Example 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

Does NOT Trigger

Distinction from deep-research

Agent Team (12 Agents)

Output Formats

Text Formats

LaTeX (.tex + .bib), DOCX (via Pandoc), PDF (via LaTeX or Pandoc), Markdown.

Figures

When the paper contains quantitative results, the visualization_agent 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 \includegraphics integration code. See references/statistical_visualization_standards.md for chart type decision trees and code templates.

Citation Formats

APA 7.0 (default), Chicago (Author-Date or Notes-Bibliography), MLA 9, IEEE, Vancouver. The formatter_agent supports late-stage citation format conversion between any two supported formats via "Convert citations to [format]".

Orchestration Workflow (8 Phases)

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

Checkpoint Rules

1. Phase 0 -> 1: User must confirm Paper Configuration Record
2. Phase 2 -> 3: User must approve outline (can request restructuring)
3. Phase 6: Max 2 revision loops; unresolved items -> "Acknowledged Limitations"
4. Peer Review Critical-severity issues block progression to Phase 7
5. User can skip Phase 1 (literature) if providing own sources

Operational Modes (9 Modes)

See references/mode_selection_guide.md for details.

Quick Mode Selection Guide

Not sure? Start with plan — it will guide you step by step.

Mode Selection Logic

"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

Plan Mode: CHAPTER-BY-CHAPTER GUIDED PLANNING

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

Handoff Protocol: deep-research -> academic-paper

intake_agent automatically detects deep-research materials (RQ Brief / Bibliography / Synthesis / INSIGHT Collection) and skips redundant steps. See deep-research/SKILL.md Handoff Protocol for the complete handoff material format.

Failure Paths

See references/failure_paths.md for details. Quick reference:

Full Academic Pipeline

See academic-pipeline/SKILL.md for the complete workflow.

Phase 0: Configuration Interview

See agents/intake_agent.md 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.

Agent File References

Reference Files

Also references from deep-research:

• deep-research/references/apa7_style_guide.md — base APA 7 reference (this skill extends, not duplicates)

Templates

Examples

Quality Standards

Writing Quality

1. Every claim must have a citation or be supported by the paper's own data
2. Zero citation orphans — in-text citations <-> reference list must perfectly match
3. Consistent register — academic tone appropriate for the discipline
4. Logical flow — clear transitions between paragraphs and sections
5. Word count compliance — within +/-10% of target

Bilingual Abstract Quality

6. Independent writing — zh-TW and EN abstracts are independently composed, NOT mechanical translations
7. Structural alignment — both abstracts cover the same key points in the same order
8. Keywords — 5-7 per language, reflecting the paper's core concepts
9. Word count — EN: 150-300 words; zh-TW: 300-500 characters

Citation Quality

10. Format compliance — 100% adherence to selected citation style
11. DOI inclusion — every source with a DOI must include it
12. Currency — flag sources older than 10 years (unless seminal works)
13. Self-citation ratio — flag if >15%

Peer Review

14. Five dimensions — Originality (20%), Methodological Rigor (25%), Evidence Sufficiency (25%), Argument Coherence (15%), Writing Quality (15%)
15. Actionable feedback — every criticism must include a specific suggestion
16. Max 2 revision rounds — unresolved items become Acknowledged Limitations

Mandatory Inclusions

17. AI disclosure statement — every paper must include a statement on AI tool usage
18. Limitations section — explicitly discuss study limitations
19. Ethics statement — when applicable (human subjects, sensitive data)

Output Language

Follows the user's language. Academic terminology is kept in English. Bilingual abstracts are always provided regardless of the main text language.

Integration with Other Skills

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 loop

Version History