MitakaKuma/BaT-SFT-data
Viewer • Updated • 9.96k • 43
Benchmark-as-Teacher
Turning benchmark to data generation and post-training infrastructure in agentic AI
-
-
MitakaKuma/BaT-RL-data
Viewer • Updated • 126 • 61 -
MitakaKuma/BaT-Qwen3.5-4B-0815
Image-Text-to-Text • 5B • Updated • 5 -
MitakaKuma/BaT-Qwen3.5-9B-0815
Text Generation • 9B • Updated • 7 -
AutoMedBench Lite Leaderboard
🩺Average scores across all seven AutoMedBench Lite tracks.
-
BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics
Paper • 2608.16211 • Published • 1 -
MitakaKuma/AutoMedBench-Lite-release
Updated • 525 -
MitakaKuma/AutoMedBench-Full-release
Updated • 364 -
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models
Paper • 2606.01961 • Published • 26