worldbench / awesome-ai-auto-research
🔥 A Survey on AI Auto-Research
Why this job: name: awesome
What it does
- Artifact generation outpaces verification. Generated ideas can appear novel yet weaken after implementation; generated code may run but implement the wrong algorithm; fluent prose can conceal unsupported claims.
- Capability boundaries emerge on open-ended tasks. Performance drops sharply for genuinely novel ideas, long-horizon experiments, and scientific judgment.
- Human-governed collaboration is most credible. AI should reduce mechanical friction while researchers retain responsibility for interpretation, experimental design, and accountability.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 6 days ago
- Stars
- 574
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- HTML
- 100% of the code
Is it looked after?
- Contributors
- 20
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 38 merged
- 2 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| brycewang-stanford / Auto-Research-Skills | 246 | 7 days ago | CC0-1.0 | No downloads |
| WecoAI / awesome-autoresearch | 1,077 | 3 months ago | CC0-1.0 | No downloads |
| Promethe-us / awesome-jev | 149 | 14 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- HTML 100%
Topics
- agent
- agentic-ai
- ai
- ai-research
- ai-scientist
- auto-research
- large-language-models
- llm
- multi-agent-system
- rag
Project record
- JobLists and guides
- StatusListed
- Commits78
- Forks61
- Watching15
- Stars in 28 days+31
- CreatedMar 29, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026