academic-writing

A preprint estimates that by the end of 2025, 89% of open-access biomedical papers show signs of LLM-assisted writing, using a new word-frequency-based method.

This paper proposes StructPO, a structure-aware policy learning framework that internalizes multi-stage academic writing workflows into a single-pass LLM policy using explicit stage tokens and refinement-guided optimization, improving introduction generation quality and efficiency.

HKUST Assistant Professor Luo Yuyu released the open-source project Supervisor-Skills, which distills ten years of research experience into AI skills executable by large models, covering topic selection, writing, reviewing, etc., aiming to become an AI co-supervisor for researchers.

Introduces GRASP, a framework that combines LLM planning with graph algorithms to generate high-fidelity related work sections by modeling inter-paper relationships through a two-layer graph structure and Steiner tree pruning.

The tweet claims that Claude has a secret 'Research Accelerator' mode using 13 prompts to quickly process research papers into various outputs.

Bibby AI is an editor-native platform that integrates the academic writing pipeline from literature discovery to submission, using agents that operate on document syntax representations to perform citation insertion, structural edits, and formatting.

This paper introduces SEFORA, a public corpus of instructor feedback on student essays, and UniMatch, a reference-based evaluation framework for assessing LLM-generated feedback. Experiments show that current LLMs struggle to match instructor feedback, achieving at most 0.4 F1.

Paper Lifecycle is a suite of Codex skills designed for academic writing, comprising two skills: Review Revision and Rebuttal Response, which help researchers improve paper quality and handle reviewer feedback.

The Stanford REAP team has launched CoPaper.AI, a tool that can automatically generate a reproducible empirical paper with complete Stata/R code and charts within 30 minutes after inputting raw data, aiming to end the manual labor of traditional papers.

The open-source project nature-skills provides an AI skill package that helps users elevate academic paper writing and scientific figure creation to Nature journal standards, supporting automatic generation of standardized charts and language polishing.

一份覆盖200+主流期刊的Claude Code/Codex期刊论文写作技能包，包含从选题到审稿回复的全流程，开源在GitHub上。

Paper2Any is an open-source project that automatically generates academic materials such as model architecture diagrams, PPT presentations, and experiment charts from paper PDFs, screenshots, or text. It supports editing and one-click Docker deployment.

Academic Paper Skills is a paper writing skill framework for Claude Code, dividing the writing process into two phases: strategy and composition. It incorporates features like literature support, reviewer simulation, and quality checks to help users generate a first draft from a research idea.

PaperDebugger is an open-source multi-agent system from NUS that integrates with Overleaf to help rewrite academic papers in real time.

A team from NUS open-sourced PaperDebugger, a multi-agent system that lives inside Overleaf, providing real-time rewriting, critique, and citation assistance with an open enhancer model (XtraGPT-7B), making Overleaf a full research environment.

Introduces an open-source AI tool called Academic Research Skills that automates the entire academic research process from topic selection to writing and peer review through collaboration of 13 agents. It can be installed as a Claude Code plugin, turning academic research into a standardized production line.

An open-source project called academic-research-skills packages a complete pipeline for writing papers using Claude Code, achieving 9.4k stars on GitHub and directly addressing pain points of student users.

ScienceClaw is an AI assistant framework integrating 285 research skills, modularizing the entire research workflow into Skills. It supports connecting to databases such as PubMed, Semantic Scholar, and ArXiv, providing functions like literature search, paper deep reading, citation analysis, experimental design assistance, and writing assistance. It is suitable for advanced users who want deep customization.

This paper introduces CiteTracer, a multi-agent framework for detecting citation hallucinations in LLM-generated scientific writing, achieving high accuracy on synthetic and real-world benchmarks.

A Zhejiang University researcher shared a comprehensive PhD guide on GitHub, covering the entire research lifecycle from topic selection to rebuttals, specifically tailored for the 3D Vision direction.