arxiv:2608.23552
Seth Karten
milkkarten
AI & ML interests
Multi-agent learning
Recent Activity
published a dataset 4 days ago
PrimeIntellect/runebench-traces updated a dataset 4 days ago
PrimeIntellect/runebench-traces authored a paper about 1 month ago
Prime Agent: A Self-Improving RLM HarnessOrganizations
models 0
None public yet
datasets 5
milkkarten/programbench-processed
Viewer • Updated • 5 • 42
milkkarten/pokemon-training-data
Viewer • Updated • 93.6M • 20
milkkarten/pokemon-showdown-replays-merged
Viewer • Updated • 29.1M • 268
milkkarten/pokechamp-pretrain-data
Viewer • Updated • 94.1M • 15
milkkarten/pokechamp
Viewer • Updated • 2.13M • 390 • 7