Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs 事件

Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs arXiv:2604.18587v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated significant potential in formal theorem proving, yet state-of-the-art performance often necessitates prohibitive test-time compute via massive roll-outs or extended context windows. In this work, we address this scalability bottleneck by exploiting an informative structure in formal verification: the observation that co