research-paper-writing

Guides end-to-end ML research paper production from experiment design through conference submission.

Updated Jun 5, 2026
One-click install
npx skills add https://github.com/xu1713/openhorse --skill research-paper-writing-xu1713
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-paper-writing
Source: https://github.com/xu1713/openhorse/tree/main/openhorse/openhorse/skills/research/research-paper-writing
Command: npx skills add https://github.com/xu1713/openhorse --skill research-paper-writing-xu1713

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires semanticscholar, arxiv, habanero, requests, scipy, numpy, matplotlib, SciencePlots, and includes references (resource) and assets (resource) components.

What problem does it solve? Writing a publishable ML paper involves coordinating experiments, verified citations, statistical analysis, LaTeX formatting, and venue-specific checklists, and mistakes in any step cause desk rejections or hallucinated references. ## Core Features & Use Cases - Full Research Lifecycle: Covers project setup, literature review, experiment design, execution monitoring, statistical analysis, drafting, self-review, and submission for NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. - Verified Citation Workflow: Fetches BibTeX programmatically via Semantic Scholar, CrossRef, and arXiv APIs instead of generating citations from memory, with a mandatory 5-step verification process. - Venue Templates and Checklists: Ships official LaTeX templates and pre-submission checklists for six major conferences, including NeurIPS's 16-item mandatory checklist and ACL's Limitations section. - Use Case: A researcher with experimental results asks the agent to draft an ICML submission; the skill maps claims to experiments, verifies every citation, generates booktabs tables and colorblind-safe PDF figures, and runs a simulated reviewer pass before submission. ## Quick Start Use the research-paper-writing skill to turn my experiment results in the results/ folder into an ICML 2026 submission draft with verified citations.

Frequently Asked Questions about research-paper-writing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write an ML paper for NeurIPS or ICML with AI assistance?

Follow the phased pipeline: identify a one-sentence contribution, map each claim to an experiment, run experiments with incremental result saving, then draft using the venue's official LaTeX template. Finish with a simulated self-review round and the venue's mandatory checklist before submitting.

How do I prevent hallucinated citations in AI-generated papers?

Never generate BibTeX from memory; fetch it programmatically via DOI content negotiation from CrossRef or the Semantic Scholar API. Verify each paper exists in at least two sources, confirm the cited claim appears in the abstract, and mark unverifiable entries as [CITATION NEEDED].

What statistical tests should ML papers report for method comparisons?

Use McNemar's test for paired binary outcomes between two methods, bootstrapped 95% confidence intervals for key metrics, and Cohen's h for effect size. Always report sample sizes, number of runs, and whether error bars show standard deviation or standard error.

Does the skill include LaTeX templates for specific conferences?

Yes, it bundles official templates for ICML 2026, ICLR 2026, NeurIPS 2025, ACL, AAAI 2026, and COLM 2025, each with the correct style file, bibliography style, and example document. Page limits and anonymization rules per venue are documented in the checklists reference.

When should I use autoreason iterative refinement versus a single pass?

Use autoreason for mid-tier models on constrained tasks, where the generation-evaluation gap is largest; use single pass for very weak models or template-filling tasks. For frontier models on unconstrained tasks, critique-and-revise or single pass performs better because autoreason suffers synthesis drift.

What are the limitations of LLM-assisted paper writing?

LLMs hallucinate roughly 40% of citations without programmatic verification and can fabricate results when drafting from raw data without a structured experiment log. Human evaluation design, IRB approval, and final framing decisions still require researcher judgment.