大语言模型（LLMs）进行解释，嵌入（Embeddings）进行组织，图（Graphs）浮现：智能体驱动的科学知识编译
LLMs Interpret, Embeddings Organize, Graphs Emerge: Agent-Driven Compilation of Scientific Knowledge
浏览论文内容
中文总结 AI 辅助
本研究在ASKS系统中实现智能体驱动的科学知识编译，通过LLM生成维基视图与语义、嵌入及图规则整合变更，编译56篇论文得到可追溯研究画像，图内容关联原始来源记录。
中文摘要 AI 辅助
持续的科学工作需要一种知识载体，该载体能够跨任务传递解释并保留通往原始证据的路径。我们将这一过程称为“科学知识编译”，并在ASKS（智能体驱动的科学知识系统，Agent-Driven Scientific Knowledge System）中实现了它。对于每一份来源，大语言模型（LLM）会生成可读的维基视图和面向机器的语义表示。确定性检查会将后者转换为文档局部的图增量（GraphDelta），而嵌入几何与显式图规则会将提出的变更整合到持久状态中。每次数据摄入都是对累积知识的可检查状态转换，编译后的维基视图和图视图与保留的原始来源记录相关联。我们通过按时间顺序编译某一研究项目的56篇已发表论文来检验这一过程。分支存活情况、跨论文支持度、谱系、覆盖范围和 churn（变动）产生了以张量网络方法为核心、分支到量子多体研究、张量网络机器学习及面向量子AI方向的可追溯作者研究画像。在本次运行中，更高级的枢纽（Hub）组织保持稳定且变动率低，规范节点（Canonical-node）增长以增量式添加为主。图级别测量和导航路径保留了与编译所依据的原始来源记录的链接。
英文摘要
Sustained scientific work requires a knowledge substrate that carries interpretation across tasks and preserves paths to source evidence. We call this process \emph{scientific knowledge compilation} and implement it in ASKS, the \emph{Agent-Driven Scientific Knowledge System}. For each source, an LLM produces a readable Wiki view and machine-facing semantics. Deterministic checks convert the latter into a document-local GraphDelta, and embedding geometry together with explicit graph rules integrates the proposed changes into persistent state. Each ingest is an inspectable state transition over accumulated knowledge, with compiled Wiki and graph views linked to the preserved source record. We examine this process by chronologically compiling 56 published papers from one research program. Branch survival, cross-paper support, lineage, coverage, and churn yield a source-traceable author research portrait centered on tensor-network methods, with branches into quantum many-body research, tensor-network machine learning, and quantum-AI-oriented directions. In this run, higher-level Hub organization remains stable and low-churn. Canonical-node growth is predominantly additive. Graph-level measurements and navigation paths retain links to the source records from which they were compiled.
发表机构
- Capital Normal University（首都师范大学）
- Putian University（莆田大学）
机构由 AI 辅助整理，请以论文原文为准。
