SanSi: A Looped Typed Decision Model for System 1.5 Thinking Paper • 2610.07730 • Published 3 days ago • 1
Agent S: An Open Agentic Framework that Uses Computers Like a Human Paper • 2410.08164 • Published Oct 10, 2024 • 27
SanSi Collection SanSi: A Looped Typed Decision Model for System 1.5 Thinking (arXiv 2610.07730). Models on Ouro-1.4B and Ouro-2.6B. • 3 items • Updated about 5 hours ago
Agent S: An Open Agentic Framework that Uses Computers Like a Human Paper • 2410.08164 • Published Oct 10, 2024 • 27
SanSi: A Looped Typed Decision Model for System 1.5 Thinking Paper • 2610.07730 • Published 3 days ago • 1
Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL Paper • 2610.00574 • Published 9 days ago • 64
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery Paper • 2609.40340 • Published 9 days ago • 110
Ouro Collection a family of pre-trained Looped Language Models. • 4 items • Updated Oct 29, 2025 • 37
Optimizing Visual Generative Models via Distribution-wise Rewards Paper • 2607.02291 • Published Jul 2 • 17
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks Paper • 2606.29082 • Published Jun 27 • 44