SAP/mirrorbench
View on GitHub[KDD 2026] An automatic, extensible Framework to Evaluate User-Proxy Agents for Human-Likeness. 🌟 Star if you like it!
- Stars
- 25
- Forks
- 3
- Open beginner issues
- 0
- Indexed issues
- 1
- Dominant language
- Jupyter Notebook
- License
- Apache-2.0
- Last GitHub push
- May 18, 2026
- Latest indexed
- Sep 21, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- Code of conduct
- Beginner labels
- No beginner labels indexed
- PR merge metrics
- No merged PRs in 30d
1 open issue indexed
Loading issues
-
Proposal: evalport-sdk adapter for mirrorbench (portable eval results via EpisodeResult/RunSummary) Open
Difficulty 4/5 3-5 days Newbie friendliness 45/100
SAP/mirrorbench#14 ·