作者位次 #5/8ACL 2026Poster· Natural Language Processing
E con P rover: Towards More Economical Test-Time Scaling for Automated Theorem Proving
Mukai Li · Linfeng Song · Zhenwen Liang · Jiahao Xu · Shansan Gong · Qi Liu · Haitao Mi · Dong Yu
摘要
Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP), attaining substantial performance gains through widely adopted test-time scaling strategies, notably reflective Chain-of-Thought (CoT) reasoning and increased sampling passes. However, they both intr...