学术写作

01 aipoch/open-science 开源 AI 研究工作台，搭载 scientific agents，专注于可复现的研究与发现。Open-Source AI research workbench with scientific agents for reproducible research and discovery. 证据综述 系统综述 实验与代码复现 Agent 智能体 TypeScript +245/周 3,127 ★ 02 HiLab-git/SSL4MIS 半监督学习在医学图像分割中的应用，含文献综述与代码实现合集Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations. 证据综述 系统综述 多模态 Python 2,671 ★ 03 hymie122/RAG-Survey 收录 AIGC 领域 RAG 的优秀论文。我们在论文 "Retrieval-Augmented Generation for AI-Generated Content: A Survey" 中提出了 RAG 基础、增强与应用分类法。Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey". 证据综述 系统综述 写作 RAG 检索增强 1,790 ★ 04 ChaokunHong/MetaScreener AI 驱动的系统综述摘要与 PDF 高效筛选工具AI-powered tool for efficient abstract and PDF screening in systematic reviews. 证据综述 系统综述 PDF引用 工程化 Python 1,326 ★ 05 asreview/asreview 系统综述中的主动学习Active learning for systematic reviews 证据综述 系统综述 引用 工程化 Python +7/周 981 ★ 06 REMath/literature_review 面向机器码的程序分析研究综述Survey of program analysis research with a focus on machine code 证据综述 系统综述 工程化 +7/周 612 ★ 07 vitorfs/parsifal Parsifal 是一个辅助研究人员开展系统文献综述（SLR）的工具Parsifal is a tool to assist researchers to perform Systematic Literature Reviews 证据综述 系统综述 引用 工程化 Python 510 ★ 08 karpathy/researchpooler 自动化研究论文的发现与分析。例如，让计算机自动打开与任意 URL 论文最相似的文献，或找出在某数据集上报告结果的全部论文，重新定义文献综述Automating research publications discovery and analysis. For example, ever wish your computer could automatically open papers that are most similar to a paper at an arbitrary url? How about finding all papers that report results on some dataset? Let's re-imagine literature review. 证据综述 系统综述 写作 RAG 检索增强 Python 496 ★ 09 khoj-ai/openpaper Open Paper 是用于管理研究文献库的工作台，集阅读、批注与理解于一体，可借助 AI 助手开展文献综述Open Paper is a workbench for managing your research library. Read, annotate, and understand your papers all in one place. Use an AI assistant to conduct your literature review. 证据综述 系统综述 PDF 阅读与问答批注与知识笔记 PDF写作 RAG 检索增强 Python +4/周 412 ★ 10 JeffffffFu/Awesome-Differential-Privacy-and-Meachine-Learning 差分隐私联邦学习系统综述（ACM Survey）；Adap dp-fl：自适应噪声的差分隐私联邦学习（TrustCom'2022）Differentially private federated learning: A systematic review (ACM Survey); Adap dp-fl: Differentially private federated learning with adaptive noise (TrustCom'2022) 证据综述 系统综述 引用 安全与风险 Python 388 ★ 11 yogsoth-ai/de-anthropocentric-research-engine 900+ 纯 Markdown 技能，用于自主 AI 研究，组织为 9 个自由组合的包，覆盖 4 层层级结构（Campaign → Strategy → Tactic → SOP）。支持带回溯的非线性编排，集成 6 个 MCP。AI 即研究员，你来指明方向。900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction. 证据综述 系统综述 文献检索与全文获取研究设计与方法 MCPSkill Agent 智能体 HTML +8/周 382 ★ 12 westlake-repl/Recommendation-Systems-without-Explicit-ID-Features-A-Literature-Review 预训练基础推荐模型论文清单Paper List of Pre-trained Foundation Recommender Models 证据综述 系统综述 写作 工程化 368 ★ 13 Aperivue/medsci-skills 面向医学研究的 Agent Skills——文献检索、报告规范与引用核查、统计、发表图表、投稿。兼容 Claude Code、Codex、Cursor 与 GitHub Copilot。由医师-研究者构建，在真实发表论文上验证。MIT 协议。Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & GitHub Copilot. Built by a physician-researcher, tested on real publications. MIT. 证据综述 系统综述 科研图表与表格文献检索与全文获取 引用写作 Agent 智能体 Python 269 ★ 14 lingzhi227/agent-research-skills Claude Code 的 skills —— deep-research：系统性学术文献综述Skills for Claude Code — deep-research: systematic academic literature review 证据综述 系统综述 Agent 智能体 Python +7/周 266 ★ 15 anoopkcn/obsidian-reference-map 用于文献综述与发现的参考文献及引文图谱Reference and citation map for literature review and discovery 证据综述 系统综述 引用 工程化 TypeScript 250 ★ 16 iSEngLab/AwesomeLLM4APR [TOSEM 2026] 大语言模型在自动化程序修复中的系统文献综述[TOSEM 2026]A Systematic Literature Review on Large Language Models for Automated Program Repair 证据综述 系统综述 引用 工程化 244 ★ 17 VisionVerse/RemoteSensing-Restoration-Survey [ISPRS 2026] 遥感图像去雾：进展、挑战与前景的系统综述[ISPRS 2026] Remote Sensing Image Dehazing: A Systematic Review of Progress, Challenges, and Prospects 证据综述 系统综述 引用 多模态 Python 231 ★ 18 Epsilon617/Codex-Academic-Skills 适用于 OpenAI Codex 的研究类 skills 精选清单，覆盖写作、文献综述、评估与研究工作流A curated list of research-oriented skills usable in OpenAI Codex, covering writing, literature review, evaluation, and research workflows. 证据综述 系统综述 写作 评测基准 Python 169 ★ 19 sisinflab/adversarial-recommender-systems-survey 本综述目标有二：(i) 综述对抗机器学习（AML）在推荐系统（RS）安全上的最新进展，即攻击与防御推荐模型；(ii) 展示 AML 在生成对抗网络（GAN）生成应用中的成功应用，得益于其学习（高维）数据分布的能力。本文对发表于主流 RS 与 ML 期刊会议的 74 篇文献进行了详尽综述，可作为 RS 社区在推荐系统安全及利用 GAN 提升生成模型质量方面的参考The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions. In this survey, we provide an exhaustive literature review of 74 articles published in major RS and ML journals and conferences. This review serves as a reference for the RS community, working on the security of RS or on generative models using GANs to improve their quality. 证据综述 系统综述 安全与风险 166 ★ 20 hubertjb/dl-eeg-review 深度学习与 EEG 系统文献综述的补充材料Supplementary material for systematic literature review on deep learning and EEG. 证据综述 系统综述 多模态 Python 159 ★ 21 drshahizan/SLR-FC 使用 AI 的系统文献综述（SLR）借助人工智能技术，自动加速海量学术文献的审阅与综合过程Systematic Literature Review (SLR) using AI involves leveraging artificial intelligence techniques to automate and expedite the process of reviewing and synthesizing large volumes of scholarly literature. 证据综述 系统综述 引用 工程化 151 ★ 22 drshahizan/obsidian Obsidian.md 是一款专为学术写作打造的出色笔记应用。本仓库是"使用 AI 进行系统文献综述"研讨会活动的组成部分。Obsidian.md stands out as an exceptional note-taking application tailored specifically for academic writing. This repository is part of the activities for the Systematic Literature Review using AI workshop. 证据综述 系统综述 批注与知识笔记大纲与论文起草 引用写作 工程化 HTML 137 ★ 23 rushei1/lazy-researcher-toolkit 一个全栈 AI 驱动应用，自动抓取、摘要、聚类并格式化研究论文为结构化文献综述——为研究者节省大量人工时间。A full-stack AI-powered application that automatically fetches, summarizes, clusters, and formats research papers into a structured literature review — saving researchers hours of manual effort. 证据综述 系统综述 Agent 智能体 Python 132 ★ 24 clover-Saber/Review-Helper Review Helper 是一款 AI 工具，帮助研究者快速摘要、整理和评估学术论文。它通过自动化关键任务来简化文献综述流程，使研究更高效、更准确。Review Helper is an AI tool that helps researchers quickly summarize, organize, and evaluate academic papers. It streamlines literature reviews by automating key tasks, making research more efficient and accurate. 证据综述 系统综述 评测基准 JavaScript 127 ★ 25 paulamartingonzalez/Targeted_Literature_Reviews_via_webscraping 针对给定查询进行网页爬取以获取文章，返回包含标题、摘要、DOI 和参考文献的电子表格。Web scraping to get articles for a given query. It returns an spreadsheet with titles, abstracts, doi and references of the article 证据综述 系统综述 文献检索与全文获取 RAG 检索增强 Jupyter Notebook 125 ★ 26 elizagrames/litsearchr litsearchr 是一个 R 包，利用关键词共现网络部分自动化系统综述的检索词选择，除识别检索词外，还能编写布尔检索式并翻译为 50 余种语言。litsearchr is an R package to partially automate search term selection for systematic reviews using keyword co-occurrence networks. In addition to identifying search terms, it can write Boolean searches and translate them into over 50 languages. 证据综述 系统综述 翻译与 OCR 翻译引用 工程化 R 125 ★ 27 littlelelephant/literature-review-agent 基于 LangGraph 的 Agent，支持文献检索、证据筛选、大纲生成以及基于证据的综述撰写。A LangGraph-powered agent for literature search, evidence screening, outline generation, and evidence-grounded review writing. 证据综述 系统综述 文献检索与全文获取 写作 Agent 智能体 Python 122 ★ 28 PouriaRouzrokh/LatteReview LatteReview Python 包的官方仓库。LatteReview 是一个低代码 Python 包，旨在通过 AI 驱动的 Agent 自动化系统文献综述流程。This is the repository for the LatteReview python package. LatteReview is a low-code Python package designed to automate systematic literature review processes through AI-powered agents. 证据综述 系统综述 Agent 智能体 Jupyter Notebook 119 ★ 29 htlin222/meta-pipe 由 Claude Code 驱动的端到端元分析自动化：AI 辅助文献综述、筛选、提取、分析与稿件生成，面向系统综述和临床证据合成。Claude Code-powered end-to-end meta-analysis automation: AI-assisted literature review, screening, extraction, analysis, and manuscript generation for systematic reviews and clinical evidence synthesis 证据综述 系统综述 Meta 分析与证据综合 引用写作 Agent 智能体 Python 115 ★ 30 asreview/synergy-dataset SYNERGY——系统综述研究筛选的开放机器学习数据集SYNERGY - Open machine learning dataset on study selection in systematic reviews 证据综述 系统综述 引用 评测基准 Python 111 ★ 31 stephenlzc/AI-Powered-Literature-Review-Skills AI驱动的系统性学术文献回顾工具 | AI-Powered Literature Survey Tool with 8-Phase Workflow & Agent Swarm Architecture 证据综述 系统综述 文献与引用管理 引用Skill Agent 智能体 Python +4/周 110 ★ 32 xinyi-hou/LLM4SE_SLR Large Language Models for Software Engineering: A Systematic Literature Review（面向软件工程的大语言模型：系统文献综述）Large Language Models for Software Engineering: A Systematic Literature Review 证据综述 系统综述 工程化 TeX 107 ★ 33 synlp/RRG-Review 综述论文"A Systematic Review of Deep Learning-based Research on Radiology Report Generation"的官方 GitHub 仓库The official GitHub repository of the survey paper "A Systematic Review of Deep Learning-based Research on Radiology Report Generation". 证据综述 系统综述 引用写作 多模态 TeX 100 ★ 34 drshahizan/obsidian-slr 本仓库托管一个为开展系统文献综述（SLR）定制的 Obsidian vault，是"使用 AI 进行系统文献综述"研讨会活动的组成部分。This repository hosts an Obsidian vault tailored for conducting a Systematic Literature Review (SLR). This repository is part of the activities for the Systematic Literature Review using AI workshop. 证据综述 系统综述 引用 工程化 92 ★ 35 keemanxp/slr-prisma 一项 Claude skill，引导你按照 PRISMA 2020 框架撰写系统文献综述。A Claude skill that walks you through writing a systematic literature review following the PRISMA 2020 framework. 证据综述 系统综述 引用Skill写作 Agent 智能体 91 ★ 36 hs-esslingen-it-security/Awesome-LLM4SVD [TOSEM'26] Awesome-LLM4SVD，源自论文"A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models"。[TOSEM'26] Awesome-LLM4SVD from "A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models" 证据综述 系统综述 工程化 Jupyter Notebook 84 ★