Repolode
Submit
worldbench

worldbench/awesome-ai-auto-research

A curated survey and paper list covering AI-assisted automation of the full academic research lifecycle, from idea generation to peer review and dissemination.

View on GitHubWebsite
Stars
558
Forks
51
Open issues
3
Last commit
2 days ago

What is it?

Awesome AI Auto-Research is a curated collection of papers and tools that accompanies a survey on using AI to automate or assist scientific research. It organizes the academic research lifecycle into eight stages grouped into four phases: creation (idea generation, literature review, coding and experiments, tables and figures), writing, validation (peer review and rebuttal), and dissemination (turning papers into slides, posters, videos and web pages).

Each section lists work by stage and subtopic, such as LLM-based idea generation, deep research agents, paper-to-code systems, automated survey writing, and automated review generation. Entries include links to arXiv, venues, project pages and GitHub repositories where available, along with benchmarks for evaluating these systems.

The list is useful for researchers and engineers who want an overview of the field or a starting point for finding specific systems and evaluation benchmarks.

Key features

  • 01Organizes papers across eight research-lifecycle stages in four phases
  • 02Covers idea generation, literature review, code and experiments, and writing
  • 03Includes sections on peer review, rebuttal and paper dissemination
  • 04Lists benchmarks for evaluating AI research systems
  • 05Links to arXiv entries, venues and GitHub repositories where available

Use cases

  • Getting an overview of research on AI-assisted scientific discovery
  • Finding existing systems for literature review or paper-to-code tasks
  • Choosing benchmarks to evaluate idea generation or novelty assessment
  • Tracking recent papers in automated research and peer review

Things to know

  • The README is a curated paper list and survey, not runnable software, so there is no install or run path.

Topics

#ai-research#llm#agent#literature-review#peer-review#awesome-list#scientific-discovery#agentic-ai#ai#ai-scientist

FAQ

What is awesome-ai-auto-research?
A curated survey and paper list covering AI-assisted automation of the full academic research lifecycle, from idea generation to peer review and dissemination. Awesome AI Auto-Research is a curated collection of papers and tools that accompanies a survey on using AI to automate or assist scientific research. It organizes the academic research lifecycle into eight stages grouped into four phases: creation (idea generation, literature review, coding and experiments, tables and figures), writing, validation (peer review and rebuttal), and dissemination (turning papers into slides, posters, videos and web pages).
Is awesome-ai-auto-research free to use? What license does it have?
awesome-ai-auto-research is open source under the MIT license. Check the license terms before using it in commercial products.
Is awesome-ai-auto-research still maintained?
Actively maintained. The last commit to awesome-ai-auto-research was on Oct 19, 2026.
What can I use awesome-ai-auto-research for?
Getting an overview of research on AI-assisted scientific discovery Finding existing systems for literature review or paper-to-code tasks Choosing benchmarks to evaluate idea generation or novelty assessment Tracking recent papers in automated research and peer review
Where can I get awesome-ai-auto-research?
The source code and installation instructions are on GitHub: https://github.com/worldbench/awesome-ai-auto-research

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects