透過迭代式後設反思的自主科學發現

摘要

自主科學發現系統有望透過自動化假說生成與驗證過程來加速研究進展。然而，現有系統僅能在受限的搜索空間內運作，或需要預先定義研究問題，這限制其進行真正開放式探究的能力。此外，儘管這些系統能反覆疊代生成假說，但它們大多缺乏將自身累積的發現進行明確整合，以揭示複雜且相互關聯現象的能力。我們提出 DiscoPER，這是一個由大型語言模型驅動的自主框架，透過動態生成與執行程式碼來探索資料集，無需預設研究目標，從而進行開放式研究。為確保嚴謹的科學有效性，每項提出的發現都必須通過統計檢定。為克服孤立搜索的限制，我們的框架引入一種二階推理機制，定期分析自身累積的發現。透過將先前發現視為經驗數據，DiscoPER 能夠識別結構模式、混淆因素與認知缺口，主動將假說探索導向搜索空間中尚未探索的區域。透過整合工具使用，搜索空間進一步擴大，使系統能超越結構化元數據的限制，無縫處理並從影像等多模態來源中提取有用資訊，從而探索相關假說。我們在 iNatDisco 上進行評估，這是一個全新的多模態生態知識基準，其模式層級的真實標註來自同儕審查文獻。結果顯示，DiscoPER 以 72.7% 的假說支持率成功還原 9 個已知模式中的 8 個，表現優於傳統因果發現與基於大型語言模型的基準方法。消融實驗顯示，DiscoPER 的效能隨數據量增加而擴展，並驗證了二階後設反思的優勢。

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.