The Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence

• 类型：arxiv
• 标识：2609.24555
• 链接：https://arxiv.org/abs/2609.24555
• 主分类：evaluation
• 形态：benchmark
• TLDR：We introduce the Endless Exam, a benchmark spanning fourteen parameterised families of mathematical construction problems, with verifiable scores that distinguish progress before and beyond published mathematical frontiers. Each submitted object is checked automatically for validity and assigned a relative quality score against a published frontier or construction baseline, without capping improvements at 1. The benchmark draws long-term challenges from open mathematical problems and generates larger instances by varying their parameters. Compact certificates allow large constructions to be ve
• 待LLM分类：否
• 标题中文：无尽之试：当代模型迈向超智能的数学构造
• TLDR中文：我们提出 Endless Exam，一个涵盖十四个参数化数学构造问题族的 benchmark，具有可验证的分数，能够区分在已发表数学前沿之前与之后的进展。每个提交的对象会被自动检验有效性，并依据已发表前沿或构造基线获得相对质量分数，不将改进上限设为 1。该 benchmark 从开放性数学问题中汲取长期挑战，并通过改变参数生成更大规模的实例。紧凑证书使得大型构造能被快速验证
• 来源文件：
• /inbox/tom/_candidates/2026-10-01-agent-rag-longcontext-candidates.json