Running Agents 1 Isomorphic Perturbation Testing 🔍 1 Evaluate model rules for genuine logic vs shortcuts
ActivationReasoning: Logical Reasoning in Latent Activation Spaces Paper • 2510.18184 • Published Oct 21, 2025 • 2
Running Agents 1 Isomorphic Perturbation Testing 🔍 1 Evaluate model rules for genuine logic vs shortcuts
Running Agents 1 Isomorphic Perturbation Testing 🔍 1 Evaluate model rules for genuine logic vs shortcuts
Scalable Logical Reasoning Collection A collection of scalable logical reasoning tasks • 12 items • Updated Mar 2 • 2