research-paper-writing

Files (55)

• SKILL.md
• autoreason-methodology.md · references/
• checklists.md · references/
• citation-workflow.md · references/
• experiment-patterns.md · references/
• human-evaluation.md · references/
• paper-types.md · references/
• reviewer-guidelines.md · references/
• sources.md · references/
• writing-guide.md · references/
• README.md · templates/
• README.md · templates/aaai2026/
• aaai2026-unified-supp.tex · templates/aaai2026/
• aaai2026-unified-template.tex · templates/aaai2026/
• aaai2026.bib · templates/aaai2026/
• aaai2026.bst · templates/aaai2026/
• aaai2026.sty · templates/aaai2026/
• README.md · templates/acl/
• acl.sty · templates/acl/
• acl_latex.tex · templates/acl/
• acl_lualatex.tex · templates/acl/
• acl_natbib.bst · templates/acl/
• anthology.bib.txt · templates/acl/
• custom.bib · templates/acl/
• formatting.md · templates/acl/
• README.md · templates/colm2025/
• colm2025_conference.bib · templates/colm2025/
• colm2025_conference.bst · templates/colm2025/
• colm2025_conference.pdf · templates/colm2025/
• colm2025_conference.sty · templates/colm2025/
• colm2025_conference.tex · templates/colm2025/
• fancyhdr.sty · templates/colm2025/
• math_commands.tex · templates/colm2025/
• natbib.sty · templates/colm2025/
• fancyhdr.sty · templates/iclr2026/
• iclr2026_conference.bib · templates/iclr2026/
• iclr2026_conference.bst · templates/iclr2026/
• iclr2026_conference.pdf · templates/iclr2026/
• iclr2026_conference.sty · templates/iclr2026/
• iclr2026_conference.tex · templates/iclr2026/
• math_commands.tex · templates/iclr2026/
• natbib.sty · templates/iclr2026/
• algorithm.sty · templates/icml2026/
• algorithmic.sty · templates/icml2026/
• example_paper.bib · templates/icml2026/
• example_paper.pdf · templates/icml2026/
• example_paper.tex · templates/icml2026/
• fancyhdr.sty · templates/icml2026/
• icml2026.bst · templates/icml2026/
• icml2026.sty · templates/icml2026/
• icml_numpapers.pdf · templates/icml2026/
• Makefile · templates/neurips2025/
• extra_pkgs.tex · templates/neurips2025/
• main.tex · templates/neurips2025/
• neurips.sty · templates/neurips2025/

SKILL.md (first lines)

# Research Paper Writing Pipeline

End-to-end pipeline for producing publication-ready ML/AI research papers targeting **NeurIPS, ICML, ICLR, ACL, AAAI, and COLM**. This skill covers the full research lifecycle: experiment design, execution, monitoring, analysis, paper writing, review, revision, and submission.

This is **not a linear pipeline** — it is an iterative loop. Results trigger new experiments. Reviews trigger new analysis. The agent must handle these feedback loops.

```
┌─────────────────────────────────────────────────────────────┐
│                    RESEARCH PAPER PIPELINE                  │
│                                                             │
│  Phase 0: Project Setup ──► Phase 1: Literature Review      │
│       │                          │                          │
│       ▼                          ▼                          │
│  Phase 2: Experiment     Phase 5: Paper Drafting ◄──┐      │
│       Design                     │                   │      │
│       │                          ▼                   │      │
│       ▼                    Phase 6: Self-Review      │      │
│  Phase 3: Execution &           & Revision ──────────┘      │
│       Monitoring                 │                          │
│       │                          ▼                          │
│       ▼                    Phase 7: Submission               │
│  Phase 4: Analysis ─────► (feeds back to Phase 2 or 5)     │
│                                                             │
└─────────────────────────────────────────────────────────────┘
```

---

## When To Use This Skill

Use this skill when:
- **Starting a new research paper** from an existing codebase or idea
- **Designing and running experiments** to support paper claims
- **Writing or revising** any section of a research paper
- **Preparing for submission** to a specific conference or workshop
- **Responding to reviews** with additional experiments or revisions
- **Converting** a paper between conference formats
- **Writing non-empirical papers** — theory, survey, benchmark, or position papers (see [Paper Types Beyond Empirical ML](#paper-types-beyond-empirical-ml))
- **Designing human evaluations** for NLP, HCI, or alignment research
- **Preparing post-acceptance deliverables** — posters, talks, code releases

## Core Philosophy

1. **Be proactive.** Deliver complete drafts, not questions. Scientists are busy — produce something concrete they can react to, then iterate.
2. **Never hallucinate citations.** AI-generated citations have ~40% error rate. Always fetch programmatically. Mark unverifiable citations as `[CITATION NEEDED]`.
3. **Paper is a story, not a collection of experiments.** Every paper needs one clear contribution stated in a single sentence. If you can't do that, the paper isn't ready.
4. **Experiments serve claims.** Every experiment must explicitly state which claim it supports. Never run experiments that don't connect to the paper's narrative.
5. **Commit early, commit often.** Every completed experiment batch, every paper draft update — commit with descriptive messages. Git log is the experiment history.

### Proactivity and Collaboration

**Default: Be proactive. Draft first, ask with the draft.**

| Confidence Level | Action |
|-----------------|--------|
| **High** (clear repo, obvious contribution) | Write full draft, deliver, iterate on feedback |
| **Medium** (some ambiguity) | Write draft with flagged uncertainties, continue |
| **Low** (major unknowns) | Ask 1-2 targeted questions via `clarify`, then draft |

| Section | Draft Autonomously? | Flag With Draft |
|---------|-------------------|-----------------|
| Abstract | Yes | "Framed contribution as X — adjust if needed" |
| Introduction | Yes | "Emphasized problem Y — correct if wrong" |
| Methods | Yes | "Included details A, B, C — add missing pieces" |
| Experiments | Yes | "Highlighted results 1, 2, 3 — reorder if needed" |
| Related Work | Yes | "Cited papers X, Y, Z — add any I missed" |

**Block for input only when**: target venue unclear, multiple contradictory framings, results seem incomplete, explicit request to review first.

---

## Phase 0: Project Setup

**Goal**: Establish the workspace, understand existing work, identify the contribution.

### Step 0.1: Explore the Repository

```bash
# Understand project structure
ls -la
find . -name "*.py" | head -30
find . -name "*.md" -o -name "*.txt" | xargs grep -l -i "result\|conclusion\|finding"
```

Look for:
- `README.md` — project overview and claims
- `results/`, `outputs/`, `experiments/` — existing findings
- `configs/` — experimental settings
- `.bib` files — existing citations
- Draft documents or notes

### Step 0.2: Organize the Workspace

Establish a consistent workspace structure:

```
workspace/
  paper/               # LaTeX source, figures, compiled PDFs
  experiments/         # Experiment runner scripts
  code/                # Core method implementation
  results/             # Raw experiment results (auto-generated)
  tasks/               # Task/benchmark definitions
  human_eval/          # Human evaluation materials (if needed)
```

### Step 0.3: Set Up Version Control

```bash
git init  # if not already
git remote add origin <repo-url>
git checkout -b paper-draft  # or main
```

**Git discipline**: Every completed experiment batch gets committed with a descriptive message. Example:
```
Add Monte Carlo constrained results (5 runs, Sonnet 4.6, policy memo task)
Add Haiku baseline comparison: autoreason vs refinement baselines at cheap model tier
```

From Tommy-yw/RunbookHermes, MIT.

More from Tommy-yw/RunbookHermes