Stabilizing Efficient Reasoning with Step-Level Advantage Selection Paper β’ 2604.24003 β’ Published 12 days ago β’ 8
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning Paper β’ 2604.16029 β’ Published 22 days ago β’ 23
Large Language Models Align with the Human Brain during Creative Thinking Paper β’ 2604.03480 β’ Published Apr 3 β’ 6
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning Paper β’ 2604.05404 β’ Published Apr 7 β’ 42
Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation Paper β’ 2604.02368 β’ Published Mar 27 β’ 12
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper β’ 2603.16859 β’ Published Mar 17 β’ 248
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation Paper β’ 2602.24286 β’ Published Feb 27 β’ 98
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning Paper β’ 2602.08236 β’ Published Feb 9 β’ 9