AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification

  • 类型:arxiv
  • 标识:2607.11849
  • 链接:https://arxiv.org/abs/2607.11849
  • 主分类:evaluation
  • 形态:benchmark
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:This work introduces AdvancedMathBench, a benchmark suite designed to evaluate advanced mathematical reasoning capabilities, and introduces VerifierBench, consisting of 888 model-generated proof trajectories paired with expert ground truth, to evaluate whether models can correctly judge proof validity and provide sound verification rationales.
  • OpenAlex ID:W7168281436
  • OpenAlex DOI:10.48550/arxiv.2607.11849
  • DOI:10.48550/arxiv.2607.11849
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.11849
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:AdvancedMathBench:一个面向高等数学证明生成与验证的基准测试套件
  • TLDR中文:本文提出 AdvancedMathBench,一个用于评估高级数学推理能力的 benchmark 套件,并推出 VerifierBench,包含 888 条模型生成的证明轨迹及专家 ground truth,用于评估模型能否正确判断证明有效性并给出合理的验证理由。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-14-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]