AI RESEARCH
Convex Compositional Reasoning Models
arXiv CS.LG
•
ArXi:2605.23395v1 Announce Type: new Compositional energy-based models can generalize to larger combinatorial reasoning problems by reusing a learned factor energy across many local constraints. In our paper, we show that a key bottleneck in compositional reasoning is not composition itself, but the non-convex geometry of the learned energy landscape. To solve this problem, we