2 papers
cs.LG2025
AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models
Samuel Lippl, Thomas McGee, Kimberly Lopez +5
How do inference time and latent computations enable large language models (LLMs) to solve multi-step reasoning problems? We introduce AlgoTrace, a framework for tracing and steeri…
cs.AI2025
Position: We Need An Algorithmic Understanding of Generative AI
Oliver Eberle, Thomas McGee, Hamza Giaffar +2
What algorithms do LLMs actually learn and use to solve problems? Studies addressing this question are sparse, as research priorities are focused on improving performance through s…