最新研究揭示大模型在法律推理中的忠实性困境，实证分析求解与自动形式化能力的边界
arXiv:2606.16118v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong performance on reasoning tasks, but whether this reflects …
探究自动形式化系统在语义相似改写下的鲁棒性，评估AI形式化能力的可靠性。
arXiv:2511.12784v3 Announce Type: replace Abstract: Large Language Models (LLMs) have recently emerged as powerful tools for autoformalization. Despit…
探索LLM通过自动形式化将异步现实任务转化为可求解规划的新范式。
arXiv:2606.00981v1 Announce Type: new Abstract: LLMs can plan by either generating action sequences directly as a Planner or translating tasks into do…
神经符号框架通过操作树实现自动形式化，ICML 2026论文提出分解-结构-修复的创新路线，助力数学推理与AI融合。
arXiv:2604.19000v2 Announce Type: replace-cross Abstract: Statement autoformalization acts as a critical bridge between human mathematics and formal m…
深度解析Lean 4自动形式化中同义改写引发的失败模式，推动形式化验证技术发展
arXiv:2604.23135v2 Announce Type: replace Abstract: Lean 4 autoformalization has become increasingly popular in recent years, with frontier language m…