CosmosYi / AutoControl-Arena
[ICML 2026] AutoControl Arena: Frontier AI Risk Auto-Discovery Platform
Why this job: works in the areas we cover, but does not say which job it does
What it does
This design addresses a central trade-off in agent safety evaluation by combining executable environments with LLM-driven narrative flexibility:
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 28 days ago
- Stars
- 105
- +12 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 92% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 0% closed
- 1 still open
- Pull requests
- 0 merged
- 1 waiting
- Releases
- None
- Never published
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Python 92%
- JavaScript 3%
- HTML 2%
- CSS 2%
Topics
- agent
- ai-agent
- ai-agents
- ai-safety
- ai-safety-research
- alignment
- safety-alignment
- safety-evaluation
Project record
- JobOther AI tools
- StatusListed
- Commits50
- Forks5
- Watching0
- Stars in 28 days+15
- CreatedMar 8, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026