This repository accompanies the survey paper "A Survey on AI Auto-Research" and tracks papers on AI-assisted and automated scientific research, covering the full research pipeline — from idea generation and literature review through coding, writing, peer review, rebuttal, and dissemination. We also include end-to-end autonomous research systems and work on societal implications.
If you find a missing paper or a broken link, please open an issue or pull request.
If you find this repository useful, please consider citing our survey paper:
@article{kong2026aiautoresearch,
title = {A Survey on {AI} Auto-Research},
author = {Kong, Lingdong and Chow, Wei and Li, Linfeng and Wang, Song and Li, Rong and Sun, Xian and Qu, Leigang and Ng, Lai Xing and Cottereau, Beno\^{i}t R. and Zhu, Jianke and Hoi, Steven C. H. and Liu, Ziwei and Chua, Tat-Seng and Ooi, Wei Tsang},
journal = {arXiv preprint arXiv:YOUR\_ARXIV\_ID},
year = {2026}
}- Idea Generation
- Literature Review & Paper Search
- Coding & Experimentation
- Tables & Figures
- Peer Review
- Rebuttal
- Paper Writing
- Dissemination (Paper2X)
- End-to-End Systems
- Societal & Critical Perspectives
- Surveys & Curated Lists
- Tools & GitHub Repos
Systems and benchmarks for automated generation, evaluation, and refinement of scientific research ideas.
Tools and benchmarks for automated literature search, synthesis, and survey generation.
Agents and benchmarks for AI-driven coding, experimentation, hypothesis testing, and scientific software engineering.
Systems for automated generation of scientific tables, charts, figures, TikZ diagrams, and visualizations.
| Name | Paper | Venue | Code |
|---|---|---|---|
| ChartGPT | arXiv | arXiv'23 | — |
| Chain-of-Table | arXiv | arXiv'24 | — |
| MatPlotAgent | arXiv | arXiv'24 | — |
| AutomaTikZ | Paper | ICLR'24 | — |
| ArxivDIGESTables | Paper | EMNLP'24 | — |
| DeTikZify | Paper | NeurIPS'24 | — |
| DiagramAgent | Paper | CVPR'25 | — |
| AbGen | Paper | ACL'25 | — |
| StarVector | Paper | CVPR'25 | — |
| VisCoder | Paper | EMNLP Findings'25 | — |
| PlotGen | arXiv | arXiv'25 | — |
| CoDA | arXiv | arXiv'25 | — |
| PlotCraft | arXiv | arXiv'25 | — |
| ShowTable | arXiv | arXiv'25 | — |
| Table2LaTeX-RL | arXiv | arXiv'25 | — |
| VIS-Shepherd | arXiv | arXiv'25 | — |
| TeXpert | arXiv | arXiv'25 | — |
| PaperBanana | arXiv | arXiv'26 | — |
| SciFig | arXiv | arXiv'26 | — |
| SciFlow-Bench | arXiv | arXiv'26 | — |
| AutoFigure-Edit | arXiv | arXiv'26 | GitHub |
| SAIL | arXiv | arXiv'26 | — |
| TikZilla | arXiv | arXiv'26 | — |
| AI-Generated Figures: Policies & Guidelines | arXiv | arXiv'26 | — |
Automated peer review generation, analysis of AI usage in review, and bias/robustness studies.
Systems and datasets for AI-assisted author rebuttals and response generation in the peer review process.
| Name | Paper | Venue | Code |
|---|---|---|---|
| Re2 Dataset | arXiv | arXiv'25 | — |
| Insights from ICLR Rebuttal Process | arXiv | arXiv'25 | — |
| DRPG | arXiv | arXiv'26 | GitHub |
| Paper2Rebuttal | arXiv | arXiv'26 | — |
| RebuttalAgent | arXiv | arXiv'26 | — |
| Author-in-the-Loop | arXiv | arXiv'26 | — |
| Commitment Checklist | arXiv | arXiv'26 | — |
Tools and studies on AI assistance for academic writing, revision, citation, and co-authorship.
| Name | Paper | Venue | Code |
|---|---|---|---|
| CoAuthor | arXiv | arXiv'22 | — |
| CycleResearcher | arXiv | arXiv'24 | — |
| Script&Shift | Paper | CHI'25 | — |
| AI in the Writing Process | Paper | AIED'25 | — |
| FutureGen | arXiv | arXiv'25 | — |
| ScholarCopilot | arXiv | arXiv'25 | — |
| OpenDraft | — | GitHub'25 | GitHub |
| DraftMarks | arXiv | arXiv'25 | — |
| XtraGPT | arXiv | arXiv'25 | — |
| Let's Use ChatGPT to Write Our Paper! | arXiv | arXiv'25 | — |
| PaperDebugger | arXiv | arXiv'25 | GitHub |
| AI Tools Expand Impact but Contract Focus | Paper | Nature'26 | — |
| APRES | arXiv | arXiv'26 | — |
| Multi-Agent LLMs for Research Limitations | arXiv | arXiv'26 | — |
Systems that transform research papers into slides, posters, videos, websites, and other presentation formats.
| Name | Paper | Venue | Code |
|---|---|---|---|
| DOC2PPT | Paper | AAAI'22 | — |
| AutoPresent | Paper | CVPR'25 | — |
| PASS | arXiv | arXiv'25 | — |
| Talk to Your Slides | arXiv | arXiv'25 | — |
| PPTAgent | Paper | EMNLP'25 | GitHub |
| PresentAgent | arXiv | arXiv'25 | GitHub |
| Auto-Slides | arXiv | arXiv'25 | — |
| SlideGen | arXiv | arXiv'25 | — |
| Paper2Slides | — | GitHub'25 | GitHub |
| SlideTailor | Paper | AAAI'26 | GitHub |
| DeepPresenter | arXiv | arXiv'26 | GitHub |
| Office Raccoon (SenseTime) | — | Web'26 | — |
| Name | Paper | Venue | Code |
|---|---|---|---|
| P2P (Paper-to-Poster) | arXiv | arXiv'25 | — |
| Paper2Poster | arXiv | arXiv'25 | GitHub |
| PosterGen | arXiv | arXiv'25 | — |
| PosterForest | arXiv | arXiv'25 | — |
| APEX | arXiv | arXiv'26 | GitHub |
| PosterOmni | arXiv | arXiv'26 | — |
| Name | Paper | Venue | Code |
|---|---|---|---|
| Preacher | Paper | ICCV'25 | GitHub |
| Paper2Video | arXiv | arXiv'25 | GitHub |
| Paper2Web | arXiv | arXiv'25 | GitHub |
Fully integrated autonomous research pipelines that span multiple stages of the scientific process.
| Name | Paper | Venue | Code |
|---|---|---|---|
| ResearchTown | Paper | ICML'25 | GitHub |
| Agent Laboratory | arXiv | arXiv'25 | — |
| Towards an AI co-scientist | arXiv | arXiv'25 | — |
| OpenAI Deep Research | — | Web'25 | — |
| Google Deep Research | — | Web'25 | — |
| AgentRxiv | arXiv | arXiv'25 | — |
| AI-Research-SKILLs | — | GitHub'25 | GitHub |
| Biomni | — | GitHub'25 | GitHub |
| Idea2Paper | — | GitHub'25 | GitHub |
| ResearchClaw | — | GitHub'25 | GitHub |
| ARIS | — | GitHub'25 | GitHub |
| PiFlow | arXiv | arXiv'25 | — |
| Towards End-to-End Automation of AI Research | Paper | Nature'26 | GitHub |
| Idea2Story | arXiv | arXiv'26 | — |
| LabClaw | — | Web'26 | — |
| UniScientist | — | Web'26 | — |
| ASI-Evolve | — | GitHub'26 | GitHub |
| FARS | — | Web'26 | — |
| AutoResearchClaw | — | GitHub'26 | GitHub |
| OpenResearcher (2026) | arXiv | arXiv'26 | GitHub |
| Aletheia | arXiv | arXiv'26 | GitHub |
| OpenAI Is Building a Fully Automated Researcher | Article | MIT TR'26 | — |
Studies on the societal implications, risks, integrity concerns, and broader impacts of AI in scientific research.
| Name | Paper | Venue | Code |
|---|---|---|---|
| Navigating the Jagged Technological Frontier | Paper | Org. Sci.'25 | — |
| Reassessing Academic Integrity in the Age of AI | Paper | SSH Open'25 | — |
| The AI Deskilling Paradox | Paper | CACM'25 | — |
| Hidden Pitfalls of AI Scientist Systems | arXiv | arXiv'25 | — |
| Rethinking Science in the Age of AI | arXiv | arXiv'25 | — |
| Measuring AI Ability to Complete Long Tasks | Blog | METR'25 | — |
| Towards a Science of Scaling Agent Systems | arXiv | arXiv'25 | — |
| AI Tools Expand Impact but Contract Focus | Paper | Nature'26 | — |
| AI for Scientific Discovery is a Social Problem | Paper | Patterns'26 | — |
| Research Integrity in the Age of AI | arXiv | arXiv'26 | — |
| SciSciGPT | Paper | Nature CS'26 | — |
| SimStep | arXiv | arXiv'25 | — |
| ConvoLearn | arXiv | arXiv'26 | — |
| AFIM: Academic Fraud Inclination Metric | Web | Web'26 | — |
| AI Researchers' Views on Automating AI R&D | arXiv | arXiv'26 | — |
| AI Scientists Are Changing Research (Editorial) | Paper | Nature'26 | — |
| Learning by Creating (Talk) | Video | Talk'26 | — |
Survey papers and curated reading lists that provide an overview of AI for scientific research.
| Name | Paper | Venue | Code |
|---|---|---|---|
| LLM4SR | arXiv | arXiv'25 | — |
| From Automation to Autonomy | arXiv | arXiv'25 | — |
| AI4Research | arXiv | arXiv'25 | — |
| A Survey of AI Scientists | arXiv | arXiv'25 | — |
| LLMs for Scientific Idea Generation: Survey | arXiv | arXiv'25 | — |
| LLMs for Automated Scholarly Paper Review: Survey | Paper | Inf. Fusion'25 | — |
| awesome-ai-research-writing | — | GitHub'24 | GitHub |
| Awesome-LLM-Scientific-Discovery | — | GitHub'25 | GitHub |
Open-source tools, frameworks, and curated resource lists for AI-assisted research (not directly tied to a single paper).
| Repository | Stars | Description |
|---|---|---|
| Awesome-Deep-Research | ~684 | Up-to-date collection of agentic deep research resources |
| Awesome-Scientific-Language-Models | ~647 | Survey of scientific LLMs (EMNLP'24) |
| Awesome-LLM-Scientific-Discovery | ~319 | Three-level autonomy framework (EMNLP'25) |
| Awesome-AI-Scientist-Papers | ~136 | Resources on AI Scientist systems |
| Awesome-Auto-Research-Tools | ~129 | Automated research tools catalog |
| awesome-autoresearch | — | Autonomous improvement loops and research agents |
| Repository | Stars | Description |
|---|---|---|
| Virtual-Scientists | ~66 | VirSci: multi-agent collaborative idea generation (ACL'25) |
| ResearchAgent | ~29 | Iterative idea proposal with reviewing agents |
| Repository | Stars | Description |
|---|---|---|
| paper-qa | ~8,300 | PaperQA2: superhuman RAG for scientific Q&A |
| local-deep-research | ~4,200 | Fully local deep research |
| researchgpt | ~3,500 | Conversational interaction with research papers |
| gpt-researcher | — | Autonomous agent for comprehensive online research |
| AutoSurvey | ~462 | Automated comprehensive literature surveys |
| storm | — | Wikipedia-style article generation (STORM) |
| Repository | Stars | Description |
|---|---|---|
| autoresearch (Karpathy) | ~55,400 | Autonomous ML experiments, ~12 exp/hour overnight |
| Paper2Code | ~4,300 | Multi-agent ML paper to code transformation |
| RD-Agent | — | Microsoft's LLM framework for autonomous data science |
| MLAgentBench | ~334 | 13 end-to-end ML experimentation tasks |
| SWE-bench | — | Real-world GitHub issue resolution benchmark |
| Repository | Stars | Description |
|---|---|---|
| paper-reviewer | ~824 | arXiv paper reviews + blog posts |
| ai-peer-review | ~123 | Multi-LLM reviews + meta-review synthesis |
| openreviewer | ~9 | Llama-8B fine-tuned on 79K expert reviews |
Last updated: 2026-04-08 · Maintained by WorldBench