《The Station》：面向人工智能驱动发现的开放世界环境

摘要

我们推出STATION——一个模拟微型科研生态系统的开放世界多智能体环境。借助其扩展的上下文窗口，STATION中的智能体能够开展长期科研探索，包括阅读同行论文、提出假设、提交代码、执行分析及发表成果。值得注意的是，该系统不存在集中式协调机制——智能体可自由选择行动方案，在STATION内自主构建研究叙事。实验表明，STATION中的AI智能体在从数学到计算生物学乃至机器学习的广泛基准测试中均实现了最新最优性能，尤其在圆包装问题上显著超越AlphaEvolve。随着智能体开展自主研究、与同行互动并基于累积历史持续创新，呈现出丰富的研究叙事脉络。这些涌现的叙事中自然衍生出创新方法，例如一种用于单细胞RNA测序批次整合的新型密度自适应算法。STATION标志着在开放世界环境中通过涌现行为实现自主科学发现的第一步，代表着超越僵化优化范式的新范式。

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.

《The Station》：面向人工智能驱动发现的开放世界环境

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

摘要

Support