通过迭代元反思实现自主科学发现

摘要

自主科学发现系统通过自动化假设生成与验证过程，有望加速科研进展。然而，当前系统通常运行在受限搜索空间内，或需预定义研究问题，限制了其真正开放式探索的能力。此外，尽管这些系统能迭代生成假设，但它们大多缺乏显式综合自身累积发现以揭示复杂互联现象的能力。为此，我们提出DiscoPER——一种基于大型语言模型的自主框架，它通过动态生成并执行代码来探索数据集，无需预设研究目标，从而开展开放式研究。为确保严格的科学有效性，每项提议的发现必须通过统计检验。为突破孤立搜索的局限性，该框架引入一种二阶推理机制，定期分析自身累积发现。通过将先前发现视为经验数据，DiscoPER识别结构模式、混淆因素及认知缺口，主动将假设探索导向搜索空间中未涉足的领域。通过融入工具使用，搜索空间进一步扩展——系统能够无缝处理并提取图像等多模态来源中的有用信息，从而探索超越结构化元数据的假设。我们在iNatDisco（一个从同行评审文献中获取模式级真实标注的新型多模态生态知识基准）上评估，DiscoPER以72.7%的假设支持率恢复了9个已知模式中的8个，性能优于经典因果发现和LLM引导的基线方法。消融实验表明，DiscoPER随数据量增加而扩展，并证实了二阶元反思的效益。

English

Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation. However, current systems operate within constrained search spaces or require predefined research questions, limiting their capacity for true open-ended inquiry. Furthermore, while they generate hypotheses iteratively, they largely lack the ability to explicitly synthesize their own accumulated findings to uncover complex, interconnected phenomena. We introduce DiscoPER, an autonomous large language model-powered framework that conducts open-ended research by dynamically generating and executing code to explore datasets without pre-specified research objectives. To ensure rigorous scientific validity, every proposed discovery must pass statistical testing. To overcome the limitations of isolated search, our framework introduces a second-order reasoning mechanism that periodically analyzes its own accumulated discoveries. By treating prior discoveries as empirical data, DiscoPER identifies structural patterns, confounds, and epistemic gaps, actively redirecting hypothesis exploration toward uncharted regions of the search space. The search space is further expanded by incorporating tool use, enabling the system to explore hypotheses beyond structured metadata by seamlessly processing and extracting useful information from multimodal sources like images. Evaluated on iNatDisco, a new multimodal ecological knowledge benchmark with pattern-level ground truth obtained from peer-reviewed literature, DiscoPER recovers 8 of 9 known patterns with a 72.7% hypothesis support rate, outperforming both classical causal discovery and LLM-guided baselines. Ablations show that DiscoPER scales with more data, and confirms the benefits of second-order meta-reflection.