Agent-Driven Scientific Knowledge System
LLMs Interpret, Embeddings Organize, Graphs Emerge: Agent-Driven Compilation of Scientific Knowledge
Researchers can use ASKS to map research trajectories and track knowledge evolution across papers, with all changes traceable to original sources.
The ASKS system compiles scientific knowledge using LLMs to interpret papers and create Wiki views and machine semantics.
It processes 56 papers chronologically, converting them into document-local GraphDeltas with embedding geometry.
The system generates a research portrait centered on tensor-network methods with branches into quantum many-body research and tensor-network machine learning.
Each ingest creates inspectable state transitions with preserved source records.
LLMs Interpret, Embeddings Organize, Graphs Emerge: Agent-Driven Compilation of Scientific Knowledge
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.
This report is categorized under AITOP's "Models" desk. Key entities and technical topics under continuous tracking include ASKS, LLMs, scientific knowledge compilation, tensor-network methods.
Source attribution: curated from arXiv cs.AI (@Shi-Ju Ran, Kun Zhang, Xi Wu, Liu-Si Yang, Wen-Jun Li).
