Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics Paper • 2609.38847 • Published Sep 30 • 12
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis Paper • 2609.38923 • Published Sep 30 • 59
SenseNova-U1.5: Towards Native Unified Visual Intelligence Paper • 2609.11929 • Published Sep 10 • 139