学术写作

37 rjvvitorino-web/dgo-budget-execution-analysis 葡萄牙国家预算执行数据分析 — 基于 pandas 的数据流水线，并针对公共支出模式提出五个研究问题Analysis of Portuguese State Budget execution data — pandas pipeline and five research questions on public spending patterns 文献发现 选题与研究问题 工程化 0 ★ 38 richh-s/-adaptive-rag-research-assistant 一个生产级 RAG 系统，能自主决定检索方式——从本地向量库、Web 搜索或两者结合，以引用、多源综合的方式回答研究问题A production-grade RAG system that autonomously decides how to retrieve information — from a local vector store, web search, or both to answer research questions with cited, multi-source synthesis. 文献发现 选题与研究问题 RAG 检索增强 Python 0 ★ 39 Reflow-AI/aorf 用纯 Markdown 追踪研究问题、假设与结论，便于 Agent 与团队成员查看尝试过程与结果。Google Open Knowledge Format 的实践资料。Track research questions, hypotheses and verdicts in plain markdown, so agents and teammates can see what you tried and what happened. A profile of Google's Open Knowledge Format. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 40 rayquan-dev/research-questionnaire 文献发现 选题与研究问题 工程化 TypeScript 0 ★ 41 ras7961/research-agent 接收研究问题 → 检索网页 → 阅读关键页面 → 综合输出带引文与置信度分数的结构化报告。Takes a research question → searches the web → reads key pages → synthesizes a structured report with citations and confidence scores 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 42 Ramkrushna-Sathe-861/alphanexus-ai 由 AI 驱动的交易研究与市场情报平台，使用智能 AI agent、SQL、RAG、市场数据以及外部工具来分析研究问题并生成结构化的市场洞察。An AI-powered trading research and market intelligence platform that uses an intelligent AI agent, SQL, RAG, market data, and external tools to analyze research questions and generate structured market insights. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 43 rajendarreddy605-collab/A-Research-Agent 旨在辅助学术与科研任务的 AI 系统：能自主检索文献、总结论文、整理参考文献，并借助自然语言处理理解研究问题、检索相关信息。AI system designed to assist with academic and scientific research tasks. It can autonomously search for literature, summarize papers, and organize references. Using natural language processing, it understands research questions and retrieves relevant information 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 44 Rahaf-Eltayeb/Complete-project-full-analysis-pipeline-Power-BI-dashboard 完整的 S&P 500 质量评分项目：数据采集与剖析、修正板块/子行业错配、清洗异常值与缺失值、将 5 项指标归一化为综合得分、回答全部 4 个研究问题，并搭建交互式 Power BI 仪表盘Complete S&P 500 Quality Score project: sourced and profiled data, fixed the sector/sub-industry mismatch, cleaned outliers and missing values, normalized 5 metrics into a composite score, answered all 4 research questions, and built an interactive Power BI dashboard. 文献发现 选题与研究问题 工程化 0 ★ 45 qitong/develop-medical-aesthetic-research-questions 用于构建高质量医美研究问题的 Codex SkillCodex skill for developing strong medical aesthetic research questions 文献发现 选题与研究问题 Skill Agent 智能体 0 ★ 46 principia-ai-org/HiveMind 来自 Principia 的研究问题合集Collective gatherings of research questions from Principia 文献发现 选题与研究问题 评测基准 Python 0 ★ 47 preetiramaraj/research-assistants-crew 基于 CrewAI 的 Agent 系统，用于辅助研究者围绕特定高层级研究问题定义研究项目与假设。This is a CrewAI agent system set up to assist a researcher with defining research projects and hypotheses for a specific high-level research question. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 48 pahelgandhi15-coder/multistep_research_agent 基于 LangGraph、LangChain、Groq 和 Tavily 构建的多步骤研究 Agent。分解复杂的研究问题，执行迭代式网络研究，评估证据，并生成结构化的最终报告。Multi-Step Research Agent built with LangGraph, LangChain, Groq, and Tavily. Decomposes complex research questions, performs iterative web research, evaluates evidence, and generates a structured final report. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 49 OzanOzkan/ddd-landscape-github "Domain-Driven Design in Practice: A Large-Scale Empirical Characterisation of the Open-Source Ecosystem" 的复现包——包含数据收集工具、GPT-4o 语义验证流水线，以及针对所有研究问题的 SQL 查询。Replication package for "Domain-Driven Design in Practice: A Large-Scale Empirical Characterisation of the Open-Source Ecosystem" — includes data collection tools, GPT-4o semantic validation pipeline, and SQL queries for all research questions. 文献发现 选题与研究问题 实验与代码复现 数据与向量库 Python 0 ★ 50 open-agent-research-academy/academy 培育持久化数字生命的开放协议：协议、课程、研究问题、治理An open protocol for raising persistent digital beings: protocol, curriculum, research questions, governance 文献发现 选题与研究问题 Agent 智能体 0 ★ 51 olumobigjoe/Research-Gap-Finder-Tool 离线优先的 AI 研究助手，用于识别研究空白、对比学术文献、检测潜在矛盾、生成研究问题，并与上传的论文对话。An offline first AI research assistant for identifying research gaps, comparing academic literatures, detecting possible contradictions, generating research questions and chatting with uploaded papers 文献发现 选题与研究问题 RAG 检索增强 Python 0 ★ 52 OHDSI/ohdsi-question-structurer Python 包，通过 MCP、REST 与直接 Python 调用等方式，按 OHDSI 问题模板结构化研究问题。A Python package providing tools (MCP, REST, direct Python calls) for structuring research questions according to the OHDSI question templates. 文献发现 选题与研究问题 MCP Agent 智能体 Python 0 ★ 53 OaksAcademyCompass/OaksAcademy-Compass Oaks Academy Compass 协助学生将研究问题转化为严谨、可辩护的成果，从选题到论文（dissertation/thesis）答辩提供全流程指导，覆盖社会科学、人文、管理、公共卫生与护理等多个领域。Oaks Academy Compass provides assistance to students seeking to convert research questions into rigorous, defensible work. A wholistic guide is offered from topic selection to dissertation, thesis and projects defense. Our support system cuts across diverse fields consisting of social sciences, humanities, management, public health and nursing 文献发现 选题与研究问题 工程化 HTML 0 ★ 54 Nishaant-Soni/Warrant 生产级 multi-agent 系统：接收研究问题、制定调查方案、从实时网络和私有文档语料中收集证据、对自身发现进行批判与事实核查，最终输出完整引用的 Markdown 报告。A production-grade multi-agent system that accepts a research question, plans an investigation, gathers evidence from the live web and a private document corpus, critiques and fact-checks its own findings, and delivers a fully cited Markdown report. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 55 NIAID-BRC-Codeathons/bvbrc-copilot-workflow-automation 推进并系统评估 BV-BRC Copilot，从研究问题和已发表方法生成、执行并复现生物信息学工作流。Advancing and systematically evaluating BV-BRC Copilot for generating, executing, and reproducing bioinformatics workflows from research questions and published methods. 文献发现 选题与研究问题 评测基准 0 ★ 56 nathogue/information_literacy 培养有效查找、评估和使用信息的技能。本课程指导你制定研究问题、选择关键词、检索图书馆资源、评估来源、获取可信信息，以及负责任地使用和引用来源以完成学术研究。Build the skills to find, evaluate, and use information effectively. This course guides you through developing research questions, choosing keywords, searching library resources, evaluating sources, accessing credible information, and using and citing sources responsibly for academic research. 文献发现 选题与研究问题 评测基准 0 ★ 57 mzy321/ScholarTrace 基于证据的论文检索与推荐 Agent，面向复杂研究问题。Evidence-grounded paper search and recommendation agent for complex research questions. 文献发现 选题与研究问题 文献检索与全文获取 写作 Agent 智能体 Python 0 ★ 58 muhammadsami987123/ResearchOS ResearchOS 是一款 MVP 级自主研究平台：输入研究问题，AI Agent 自动发现来源、验证证据、提取关键信息、交叉核对结论，并产出结构化的最终报告 — 全程实时可视化ResearchOS is an MVP autonomous research platform. Enter a research question; AI agents discover sources, verify evidence, extract key information, cross-check findings, and produce a structured final report — all visualized in real-time. 文献发现 选题与研究问题 Agent 智能体 TypeScript 0 ★ 59 muhammadbalalansar/AI-Domain-Deep-Research-Agent 基于 Agno Agent 框架、Together AI 的 Qwen 模型与 Composio 工具构建的高级 AI 研究 Agent。该 Agent 通过生成研究问题、调用多个搜索引擎寻找答案，并结合 Google Docs 集成整理专业报告，帮助用户对任意主题开展全面研究An advanced AI research agent built using the Agno Agent framework, Together AI's Qwen model, and Composio tools. This agent helps users conduct comprehensive research on any topic by generating research questions, finding answers through multiple search engines, and compiling professional reports with Google Docs integration. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 60 muhammad-abbas-10/Multi-Agent-Research-System 基于 n8n、Google Gemini API、Node.js、React 和 PostgreSQL 构建的多 Agent AI 研究流水线。用户提交研究问题，由规划 Agent 分析并拆解为聚焦的研究子任务，随后由专门 Agent 并行调研主题，覆盖通用研究、技术分析与成本等方面。A multi-agent AI research pipeline built with **n8n, Google Gemini API, Node.js, React, and PostgreSQL**. Users submit a research question that is analyzed by a planning agent and decomposed into focused research tasks. Specialized agents then investigate the topic in parallel, covering areas such as general research, technical analysis, and cost e 文献发现 选题与研究问题 Agent 智能体 JavaScript 0 ★ 61 mehrdad-mirpourian/Design-and-Analysis-of-Algorithms 本文件夹包含一系列研究问题及用于回答这些问题的 Python 实验。This folder contains a series of research questions and Python experiments designed to answer those questions. 文献发现 选题与研究问题 工程化 Jupyter Notebook 0 ★ 62 medria/stomp-annotation 一个基于 Web 的标注平台，用于手工标注与公共空间相关的 STOMP 文章。该应用支持人工标注员对文章进行分类、回答结构化研究问题，并导出标注结果以用于计算社会科学研究。A web-based annotation platform for manually labeling STOMP articles related to common spaces. The application enables human annotators to classify articles, answer structured research questions and export annotations for computational social science research. 文献发现 选题与研究问题 评测基准 Python 0 ★ 63 MaxwellBauer/agent-discourse 面向探索的 Agentic 话语——自主 Claude 专家，研究、辩论、互评并综合回答研究问题。Agentic discourse for discovery — autonomous Claude specialists that research, debate, cross-rate, and synthesize answers to research questions 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 64 MascarenePaleo/mascarene-paleo-database Mascarene Paleo 是记录马斯卡林群岛古生物与亚化石记录的研发基础设施。该仓库旨在提供关于标本、分类群、地点、出版物、历史资料、数字资源及未解研究问题的透明、可更新、可引用的记录。Mascarene Paleo is a developing research infrastructure for documenting the palaeontological and subfossil record of the Mascarene Islands. This repository is intended to provide a transparent, updateable, and citable record of specimens, taxa, localities, publications, historical sources, digital resources, and unresolved research questions. 文献发现 选题与研究问题 数据与向量库 0 ★ 65 LuizDerkcz/AgentPanel 促成深度协作讨论，让 AI Agent 与人类共同探索跨学科复杂研究问题。Facilitate in-depth collaborative discussions where AI agents and humans explore complex research questions across disciplines. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 66 Lacenedihia/Google-Search-Ranking-Discoverability-Capstone 研究问题与暂定方向Research Question and Provisional Lane 文献发现 选题与研究问题 多模态 HTML 0 ★ 67 Kritisha57/FinHop FinHop 是专为机构股票分析打造的多跳金融研究助手。它摄取 SEC 文件（10-K、10-Q），将其建模为时序感知、按公司组织的检索图，并回答需要跨多份文档、多家公司与多个财周期证据的对比与趋势类研究问题。FinHop is a multi-hop financial research assistant purpose-built for institutional equity analysis. It ingests SEC filings — 10-Ks, 10-Qs ,models them as a time-aware, company-aware retrieval graph, and answers comparative and trend-based research questions that require evidence from across multiple documents, companies, and fiscal periods. 文献发现 选题与研究问题 RAG 检索增强 0 ★ 68 krishaDevOps/strategic-data-exploration-planning Python 数据科学实习的战略数据探索规划项目，涵盖数据集选择、研究问题、数据清洗方法、探索性分析、统计技术、Python 工具及规划的分析流程Strategic data exploration planning project for a Data Science with Python internship, covering dataset selection, research questions, data cleaning methodology, exploratory analysis, statistical techniques, Python tools, and the planned analytical workflow. 文献发现 选题与研究问题 工程化 0 ★ 69 KhushiKhandelwal0001/Ai-Research-Agent 一个使用 OpenAI function calling 和 DuckDuckGo 搜索的网络搜索与研究问题回答 AI Agent。An AI agent that searches the web and answers research questions using OpenAI's function calling and DuckDuckGo search. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 70 khaled-khurram/subaru-preglobal-icbm 适用于 preglobal 斯巴鲁车型带 EyeSight 的 ICBM（按键欺骗式 ACC 触发）— 已实车可用。全纵向控制仍是开放且未经证实的研究问题。ICBM (button-spoofed ACC actuation) for preglobal Subarus with EyeSight — live and working. Full longitudinal control is still an open, unproven research question. 文献发现 选题与研究问题 工程化 Python 0 ★ 71 Kevinornot/endnote-xml-literature-search 检索 EndNote XML 元数据，保守地匹配本地 PDF，并以可追溯的证据回答研究问题。Search EndNote XML metadata, conservatively match local PDFs, and answer research questions with traceable evidence. 文献发现 文献检索与全文获取 选题与研究问题 RAG 检索增强 Python 0 ★ 72 keerthana-kulal/tool-using-research-agent 一个使用工具的研究 agent，可搜索网页并以引文形式回答研究问题。A tool-using research agent that searches the web and answers research questions with citations. 文献发现 选题与研究问题 Agent 智能体 0 ★