Into the Unknown: Benchmarking AI agents on open scientific research problems
Paper • 2610.19159 • Published • 160
Seungone Kim PRO
seungone
AI & ML interests
Large Language Models, LLM-as-a-Judge, Reward Model Overoptimization, Personalized Alignment
Recent Activity
new activity 7 days ago
prometheus-eval/into-the-unknown:Add task category and sample usage authored a paper 7 days ago
Into the Unknown: Benchmarking AI agents on open scientific research problems upvoted a paper 8 days ago
Into the Unknown: Benchmarking AI agents on open scientific research problemsOrganizations
Add task category and sample usage
1
#2 opened 7 days ago
by 
nielsr
authored a
paper 7 days ago
upvoted a paper 8 days ago
submitted a
paper to Daily Papers 8 days ago
liked a
dataset 8 days ago
upvoted 2
papers 8 days ago
updated a
dataset 8 days ago
liked a
dataset 8 days ago
authored 5
papers 11 days ago
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
Paper • 2610.02202 • Published • 16
Efficient Test-Time Adaptation through Human-AI Interaction
Paper • 2609.04141 • Published
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Paper • 2608.19197 • Published • 61
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Paper • 2607.04412 • Published • 37
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
Paper • 2606.29082 • Published • 45
published a
dataset 19 days ago
liked a
dataset 22 days ago
upvoted a paper 23 days ago
upvoted a paper about 2 months ago
upvoted a paper 2 months ago
upvoted an article 3 months ago
Article
Bringing Fusion Down to Earth: ML for Stellarator Optimization
cgeorgiaw
• • 84