Direct Optimization of Generators for Search in Automated Theorem Proving
arXiv:2609.25575v1 Announce Type: cross Abstract: Fine-tuned Large Language Models (LLMs) significantly advance Automated Theorem Proving (ATP), but are often deployed as guiding policies within tree search rather than for single-attempt generation. Recent work shows cross entropy is suboptimal for…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-23 04:00 · arXiv stat.ML
Direct Optimization of Generators for Search in Automated Theorem Proving