Tag
该论文提出 DRAGO 框架，用确定性的形式化诊断替代无依据的 LLM 批评来修复 LLM 生成的形式化规范，在五个基准上将规范回归率从 11.8% 降至 1.3%，并显著提升答案准确率。
This paper introduces G-RRM, a neuro-symbolic approach that uses recurrent reasoning models to guide symbolic solvers for constraint satisfaction problems, showing significant speedups in certain conditions.