目前基于 LLM 的研究代理已经通过代理编排, 取得了进步，但在很大程度上忽视了科学知识编排。现有的作品经常将论文简化为摘要,表面提及,和平面\texttt{cites}边缘,省略关键实体,声明,证据,机制,和科学推理所必需的方法谱系。为此,，我们引入了\textbf{Agents-K1},，这是一个端到端知识编排管道，可将原始文档转换为代理本机科学知识图。 Agents-K1 在统一的理论基础下集成了三个组件: 多模态解析器，其五模块模式捕获实体, 多模态证据, 引用, 并在整篇论文中键入实体间关系，而不是单独摘要; 在基于规则的奖励下使用 GRPO 训练的 4B 信息提取骨干; 和 graphanything CLI, 统一网络搜索的三源代理接口, 多模态图检索,和跨文档遍历。在此,之上，我们处理了六个主题的246万篇科学论文，以生成\textbf{Scholar-KG},，其中我们发布了包含一百万篇论文的子集,，并且可以通过下面的SCP链接访问完整的Scholar-KG。相同的管道可以扩展到通用领域语料库和符合模式的数据合成。大量实验表明，Agents-K1在科学信息提取,知识图谱构建,和多跳科学推理方面取得了优越的性能。
Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works often reduce papers to abstracts, surface mentions, and flat \texttt{cites} edges, omitting key entities, claims, evidence, mechanisms, and method lineages essential for scientific reasoning. To this end, we introduce \textbf{Agents-K1}, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs. Agents-K1 integrates three components under a unifying theoretical foundation: a multimodal parser whose five-module schema captures entities, multimodal evidence, citations, and typed inter-entity relations across the full paper rather than abstracts alone; a 4B information-extraction backbone trained with GRPO under a rule-based reward; and a graphanything CLI, a tri-source agent interface that unifies web search, multimodal graph retrieval, and cross-document traversal. On top of this, we process 2.46 million scientific papers across six subjects to produce \textbf{Scholar-KG}, of which we release a one-million-paper subset, and the full Scholar-KG is accessible via the SCP link below. The same pipeline can be extended to general-domain corpora and to schema-conformant data synthesis. Extensive experiments demonstrate that Agents-K1 achieves superior performance in scientific information extraction, knowledge graph construction, and multi-hop scientific reasoning.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)