SoundnessBench：你的AI科学家真的能区分好的研究想法和坏的吗？
SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?
AI总结：
提出SoundnessBench基准，通过ICLR提交的1099个机器学习研究提案评估LLM判断研究想法方法论合理性的能力，发现当前LLM存在普遍乐观偏差，无法可靠作为科学严谨性的独立初筛评估者。
摘要：
自主AI研究智能体旨在通过自动化研究流程（从假设生成到同行评审）加速科学发现。然而，现有基准很少测试一个基本瓶颈：大型语言模型在投入时间和计算资源之前，能否判断研究想法的方法论可行性。我们引入了SoundnessBench，一个从ICLR提交中重建的1099个机器学习研究提案的精选基准，标注了评审者的合理性子分数，并对照源论文进行了审计。SoundnessBench应被解释为可恢复的提案阶段合理性基准，而非对完整论文评审结果的精确预测。在12个前沿LLM中，我们发现了一个普遍的乐观偏差：在标准提示下，模型经常将低合理性的提案评为合理，而激进提示则主要将错误从假阳性转移到假阴性。对公共语料污染、论文识别短语、表面特征和人工审计质量的额外控制表明，这种行为不能由单一混杂因素解释。我们的结果表明，当前LLM作为科学严谨性的独立初筛评估者尚不可靠。
英文摘要：
Autonomous AI research agents aim to accelerate scientific discovery by automating the research pipeline, from hypothesis generation to peer review. However, existing benchmarks rarely test a fundamental bottleneck: whether Large Language Models can judge the methodological viability of a research idea before expending time and computational resources. We introduce SoundnessBench, a curated benchmark of 1,099 machine-learning research proposals reconstructed from ICLR submissions, labeled with reviewer soundness sub-scores, and audited against source papers. SoundnessBench should be interpreted as a benchmark for recoverable proposal-stage soundness rather than exact prediction of full-paper review outcomes. Across 12 frontier LLMs, we find a pervasive optimism bias: under standard prompting, models frequently rate low-soundness proposals as sound, while aggressive prompting largely shifts errors from false positives to false negatives. Additional controls for public-corpus contamination, paper-identifying phrases, surface features, and human audit quality suggest that this behavior is not explained by a single confounder. Our results indicate that current LLMs are not yet reliable as standalone first-gate evaluators for scientific rigor.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
