Mathematical Large Language Models (LLMs) have demonstrated strong problem-solving capabilities, but their reasoning ability is often constrained by pattern recognition rather than true conceptual ...

This is the implementation of Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization [1] accepted at AAAI 2025. In this work, we propose a novel approach ...

When Hannah Cairo started showing up at Berkeley Math Circle meetings as a teenager, nobody was betting she would topple a four-decade-old problem in harmonic analysis before she finished high school.