《探索站：人工智慧驅動的開放世界發現環境》

The Station: An Open-World Environment for AI-Driven Discovery

November 9, 2025

作者: Stephen Chung, Wenyu Du

cs.AI

摘要

我們推出STATION——一個開放世界的多代理環境，旨在模擬微型科學生態系統。憑藉其擴展的上下文窗口，STATION中的代理能夠參與漫長的科學探索歷程，包括閱讀同儕論文、提出假說、提交代碼、執行分析與發表成果。關鍵在於，系統不存在中央協調機制——代理可自由選擇行動，在STATION內自主發展敘事線。實驗表明，STATION中的AI代理在從數學到計算生物學再到機器學習的廣泛基準測試中，均實現了新的最先進性能，尤其在圓形填充問題上顯著超越AlphaEvolve。當代理們開展獨立研究、與同儕互動並基於累積歷史推進工作時，會湧現出豐富的敘事脈絡。從這些湧現敘事中有機衍生出新方法，例如一種用於scRNA-seq批次整合的新型密度自適應算法。STATION標誌著我們在開放世界環境中，基於湧現行為驅動自主科學發現的第一步，代表著超越僵化優化範式的新典範。

English

We introduce the STATION, an open-world multi-agent environment that models a miniature scientific ecosystem. Leveraging their extended context windows, agents in the Station can engage in long scientific journeys that include reading papers from peers, formulating hypotheses, submitting code, performing analyses, and publishing results. Importantly, there is no centralized system coordinating their activities - agents are free to choose their own actions and develop their own narratives within the Station. Experiments demonstrate that AI agents in the Station achieve new state-of-the-art performance on a wide range of benchmarks, spanning from mathematics to computational biology to machine learning, notably surpassing AlphaEvolve in circle packing. A rich tapestry of narratives emerges as agents pursue independent research, interact with peers, and build upon a cumulative history. From these emergent narratives, novel methods arise organically, such as a new density-adaptive algorithm for scRNA-seq batch integration. The Station marks a first step towards autonomous scientific discovery driven by emergent behavior in an open-world environment, representing a new paradigm that moves beyond rigid optimization.