OpenFrontiers：开放研究问题语料库与科学再发现基准
原标题：OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery
AI 摘要
研究团队发布 OpenFrontiers，一个跨学科开放研究问题语料库（12,151 条记录）及配套基准 OpenFrontiers-Bench（200 道数学问题，含 Lean 4 形式化陈述）。在 HQ-50 子集上评估七个 LLM 智能体：闭卷条件下最多解出 40 道已解题中的 7 道，联网条件下最多 27 道但多为检索已发表解答，且无任何开放问题被解出。该工作为衡量研究级科学再发现能力提供了形式化评测基础。
正文节选
OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery Abstract Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level problems remains challenging. We introduce OpenFrontiers, a cross-disciplinary resource that combines a structured corpus of open research problems with a retrospective benchmark of recently resol