AI RESEARCH
Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms
arXiv CS.CL
•
ArXi:2604.15842v1 Announce Type: new Large language models (LLMs) have nstrated impressive capabilities, yet their internal mechanisms for handling reasoning-intensive tasks remain underexplored. To advance the understanding of model-internal processing mechanisms, we present an investigation of how LLMs perform arithmetic operations by examining internal mechanisms during task execution. Using early decoding, we trace how next-token predictions are constructed across layers.