https://aimojo.io/deepseek-prover-v2/
May 26, 2025 - DeepSeek-Prover-V2 sets a new benchmark in AI maths. This open-source LLM bridges human intuition and formal proof, achieving an 88.9% MiniF2F-test pass rate.
deepseekproverbridgesinformalmaths
https://aclanthology.org/2025.acl-demo.2/
Xin Quan, Marco Valentino, Danilo Carvalho, Dhairya Dalal, Andre Freitas. Proceedings of the 63rd Annual Meeting of the Association for Computational...
formal reasoningpeircematerialviallm