LLM预训练中领域数据重复的缩放规律，揭示数据重复如何影响模型性能与训练效率的边界效应。
arXiv:2608.14071v1 Announce Type: new Abstract: As large language models scale, their training-token budgets must also increase to maintain an appropr…
全新多领域科学代码搜索数据集及基准发布，填补代码检索领域空白
arXiv:2607.05443v1 Announce Type: cross Abstract: Scientists increasingly rely on open-source tools to support their research workflows, yet discoveri…
为AI Agent 解锁专业领域多维数据，高效减少调用次数与上下文消耗，贴合 Agent 工作流的信息获取基础设施。
专为 Agent 设计的 AI 搜索层服务
利用通用数据解决低资源领域大模型适配难题，为领域迁移提供新思路
arXiv:2511.07380v2 Announce Type: replace Abstract: Adapting large language models (LLMs) to low-resource domains remains challenging due to the scarc…