Intern-Atlas：作為AI科學家研究基礎設施的方法論演進圖譜

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

April 30, 2026

作者: Yujun Wu, Dongxu Zhang, Xinchen Li, Jinhang Xu, Yiling Duan, Yumou Liu, Jiabao Pan, Xuanhe Zhou, Jingxuan Wei, Siyuan Li, Jintao Chen, Conghui He, Cheng Tan

cs.AI

摘要

現有的研究基礎設施本質上以文檔為中心，僅提供論文間的引用鏈接，但缺乏對方法論演進的明確表徵。尤其未能捕捉那些解釋研究方法如何及為何出現、適應並相互借鑑的結構化關係。隨著人工智慧驅動的研究代理成為科學知識的新型消費者，此類限制日益凸顯，因為這些代理無法從非結構化文本中可靠地重構方法演進的拓扑結構。我們提出Intern-Atlas——一個方法演進圖譜，能自動識別方法層級的實體、推斷方法論間的淵源關係，並捕捉驅動連續創新間轉變的關鍵瓶頸。該圖譜基於涵蓋AI會議、期刊與arXiv預印本的1,030,314篇論文構建，包含9,410,201條語義類型化的邊緣，每條邊緣均附有逐字來源證據，形成可查詢的方法發展因果網絡。為實現該結構的實用化，我們進一步提出自引導時序樹搜索算法，用於構建追溯方法隨時間演進的演化鏈。我們通過與專家策劃的真實演化鏈對比評估圖譜質量，結果顯示高度吻合。此外，我們驗證了Intern-Atlas在創意評估與自動化創意生成等下游應用中的可行性。我們將方法演進圖譜定位為新興自動化科學發現的基礎數據層。

English

Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of methodological evolution. In particular, it does not capture the structured relationships that explain how and why research methods emerge, adapt, and build upon one another. With the rise of AI-driven research agents as a new class of consumers of scientific knowledge, this limitation becomes increasingly consequential, as such agents cannot reliably reconstruct method evolution topologies from unstructured text. We introduce Intern-Atlas, a methodological evolution graph that automatically identifies method-level entities, infers lineage relationships among methodologies, and captures the bottlenecks that drive transitions between successive innovations. Built from 1,030,314 papers spanning AI conferences, journals, and arXiv preprints, the resulting graph comprises 9,410,201 semantically typed edges, each grounded in verbatim source evidence, forming a queryable causal network of methodological development. To operationalize this structure, we further propose a self-guided temporal tree search algorithm for constructing evolution chains that trace the progression of methods over time. We evaluate the quality of the resulting graph against expert-curated ground-truth evolution chains and observe strong alignment. In addition, we demonstrate that Intern-Atlas enables downstream applications in idea evaluation and automated idea generation. We position methodological evolution graphs as a foundational data layer for the emerging automated scientific discovery.