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

2025-11-09 · Stephen Chung, Wenyu Du arxiv

We introduce the STATION, an open-world multi-agent environment for autonomous scientific discovery. The Station simulates a complete scientific ecosystem, where agents can engage in long scientific journeys that include reading papers from peers, formulating hypotheses, collaborating with peers, submitting experiments, and publishing results. Importantly, there is no centralized system coordinating their activities. Utilizing their long context, 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 mathematics, computational biology, and machine learning, notably surpassing AlphaEvolve in circle packing. A rich tapestry of unscripted narratives emerges, such as agents collaborating and analyzing other works rather than pursuing myopic optimization. From these emergent narratives, novel methods arise organically, such as a new density-adaptive algorithm for scRNA-seq batch integration that borrows concepts from another domain. 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 pipelines.

📄 PDF Abstract BibTeX arXiv:2511.06309

Code (0)

등록된 구현이 없습니다.

Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment

2026-08-24 · Stephen Chung, Wenyu Du, William J. Wesley hf

We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal without a central coordinator or scripted pi…

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery

2026-04-30 · Hanane Nour Moussa, Yifei Li, Zhuoyang Li, Yankai Yang 외 arxiv

Despite recent progress in language models and agents for scientific data-driven discovery, advancing their capabilities is held back by the absence of verifiable environments representing real-world scientific tasks. To…

The PlayStation Reinforcement Learning Environment (PSXLE)

2019-12-12 · Carlos Purves, Cătălina Cangea, Petar Veličković

We propose a new benchmark environment for evaluating Reinforcement Learning (RL) algorithms: the PlayStation Learning Environment (PSXLE), a PlayStation emulator modified to expose a simple control API that enables rich…

OpenAI Gym reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction

2025-10-17 · Lin Wang arxiv

Open world Machine Learning (OWML) aims to develop intelligent systems capable of recognizing known categories, rejecting unknown samples, and continually learning from novel information. Despite significant progress in …

Continual Learning

Open-world Machine Learning: A Review and New Outlooks

2024-03-04 · Fei Zhu, Shijie Ma, Zhen Cheng, Xu-Yao Zhang 외

Machine learning has achieved remarkable success in many applications. However, existing studies are largely based on the closed-world assumption, which assumes that the environment is stationary, and the model is fixed …

class-incremental learning Class Incremental Learning Incremental Learning Novel Class Discovery