NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
Paper • 2606.24530 • Published • 55
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
iseesaw
authored a
paper about 18 hours ago
yuruu
updated a
dataset about 19 hours ago
iseesaw
submitted a
paper to Daily Papers 2 days ago
iseesaw
authored 8
papers 3 days ago
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Paper • 2509.26628 • Published • 17
From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models
Paper • 2509.25373 • Published
JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
Paper • 2512.16649 • Published • 31
How Far Can Unsupervised RLVR Scale LLM Training?
Paper • 2603.08660 • Published • 60
Emotion-Director: Bridging Affective Shortcut in Emotion-Oriented Image Generation
Paper • 2512.19479 • Published • 1
PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
Paper • 2601.05465 • Published
MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
Paper • 2604.14564 • Published • 1
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
Paper • 2606.23654 • Published • 76
iseesaw
submitted a
paper to Daily Papers 3 days ago
yuruu
published a
dataset 4 days ago
iseesaw
authored a
paper about 1 month ago
iseesaw
authored a
paper 9 months ago
iseesaw
authored 3
papers 10 months ago