相关数据集
MedAgentBoard
MedAgentBoard是一个全面的基准测试平台，用于评估多智能体协作、单LLM和传统方法在多种医疗任务和数据模态上的性能。数据集涵盖了四个医疗任务类别：医疗（视觉）问答、非专业摘要生成、结构化电子健康记录（EHR）预测建模和临床工作流程自动化。数据集包含文本、医疗图像和结构化EHR数据，旨在解决医疗领域中多智能体协作的实际优势问题，并提供了比较不同AI方法的平台。
arXiv2025-05-18 更新1540
20210312-DOLA: Agent adapt ontologies to agree on decision taking (adaptation operators comparison)
This archive contains the results of a multi-agent simulation experiment [1] carried out with Lazy lavender [2] environment. Experiment Label: 20210312-DOLA Experiment design: Agent adapt ontologies
NIAID Data Ecosystem50
Even good bots fight: The case of Wikipedia
In recent years, there has been a huge increase in the number of bots online, varying from Web crawlers for search engines, to chatbots for online customer service, spambots on social media, and conte
NIAID Data Ecosystem20
Multi-Agent Collaborative Bayesian Optimization via Constrained Gaussian Processes
The increase in the computational power of edge devices has opened a new paradigm for collaborative analytics whereby agents borrow strength from each other to improve their learning capabilities. Thi
DataCite Commons2024-07-10 更新60
Distributed AGI Alignment as a Public Good
Current AGI alignment efforts assume a winner-take-all race. This assumption is mathematically incoherent. The CELL Series research programme—anchored in a peer-reviewed foundational paper (Kain, 2026
Zenodo2026-06-25 更新30
