Rufus-Air: An Open LLM Post-Training Recipe
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
2
Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning
1
Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning
1
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
Revisiting Complete Reasoning Traces for Post-Training
UC Berkeley Researchers Release CUA-Lite, an Open Platform Unifying Sandboxes, Data, Evaluation and RL for Computer-Use Agents
4 min1