Score
Post-Training Reinforcement Learning Agent SQL 2025-05-20

SkyRL-SQL: Simple and Data Efficient Multi-Turn RL for Text2SQL

Recent advances in RL have turned LLMs into interactive agents capable of reasoning, exploring, and executing actions. While tasks like math, web sear...

workflow
Post-Training Reinforcement Learning Agent SWE 2025-05-07

SkyRL-v0: Train Real-World Long-Horizon Agents via Reinforcement Learning
performance bars
Post-Training Reasoning 2025-02-21

S*: Test-Time Scaling for Code Generation
performance bars
Post-Training Reinforcement Learning Distillation Reasoning 2025-02-13

Unlocking the Potential of Reinforcement Learning in Improving Reasoning Models
Blue Bird Flash
Post-Training Preference-Optimization Reasoning 2025-01-23

Think Less, Achieve More: Cut Reasoning Costs by 50% Without Sacrificing Accuracy
Blue Bird
Post-Training Distillation 2025-01-10

Sky-T1: Train your own O1 preview model within $450
About
Sky Computing 2025-01-01

About Us