AgentDish directory
MLE-bench
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
#733
↓ -2
Socrates
Open-source multi-agent protocol for AI research agents. It pairs a tool-using Scientist with a question-only advisor that can only ask questions and approve plans, and the README includes quick-start setup plus notes on reproducing results on MLE-bench/Kaggle tasks. |
AI Research / Multi-agent systems | 82 | ↓ -2 | 22 days ago | Details |