1
OpenSquilla 发布 0.4.0：AI 写代码首次能“自我验证”
AI编码首次实现自我验证，通过“红绿回归”三关机制自动发现难以察觉的bug，尤其擅长数学梯度等盲区。
OpenSquilla 上线后数周内 GitHub star 增至数千量级
2
FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning
一种新型训练框架，在加速大模型数学推理训练的同时显著提升自我验证能力，精准解决LLM推理瓶颈。
arXiv:2605.28389v1 Announce Type: new Abstract: While large language models have made significant progress in mathematical reasoning, they remain unre…