Tag
OpenAI has trained a model in just 24 days that solved over 100 long-standing mathematical open problems, indicating significant progress in AI-driven mathematical research.
This paper proposes a Program-Solve interface where clinical language models generate Python code for a deterministic executor to perform math calculations, evaluating on MedCalc-Bench and finding improved accuracy for larger models like Qwen2.5-32B compared to direct arithmetic and hand-written libraries.