mlsanityData to 14 Oct 2026

LLMs Interpret, Embeddings Organize, Graphs Emerge: Agent-Driven Compilation of Scientific Knowledge

arXiv 2608.29612 ↗First posted 30 Aug 2026cs.AI cs.DL cs.IRcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Sustained scientific work requires a knowledge substrate that carries interpretation across tasks and preserves paths to source evidence. We call this process scientific knowledge compilation and implement it in ASKS, the 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 30 of its 77 references that are in the map. First posted on arXiv 30 Aug 2026.

Builds on

30 of 77 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks18 Feb
  2. 2025KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment10 Feb

Other references · 28

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  7. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  9. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  10. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  11. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  12. 2020Knowledge Graphscited by 621
16 more
  1. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  2. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  3. 2025Accelerating scientific discovery with Co-Scientistcited by 401
  4. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  5. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 267
  6. 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunitiescited by 97
  7. 2024Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Constructioncited by 70
  8. 2023A Comprehensive Survey on Automatic Knowledge Graph Constructioncited by 63
  9. 2026MiniMax Sparse Attentioncited by 44
  10. 2021Packaging research artefacts with RO-Cratecited by 24
  11. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  12. 2023Tensor networks for interpretable and efficient quantum-inspired machine learningcited by 17
  13. 2026A Programming Paradigm for Spatiotemporal Composabilitycited by 8
  14. 2021Automatically Differentiable Quantum Circuit for Many-qubit State Preparationcited by 4
  15. 2023Semantic Units: Organizing knowledge graphs into semantically meaningful units of representationcited by 4
  16. 2022Quantum compiling with a variational instruction set for accurate and fast quantum computingcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Agents-K1: Towards Agent-native Knowledge Orchestration
  2. 2026Higher-Order Knowledge Representations for Agentic Scientific Reasoning
  3. 2026Knows: Agent-Native Structured Research Representations
  4. 2025Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning
  5. 2026WFM: Wiki Foundation Model for Complex Agentic Reasoning
  6. 2026AutoKD: Autonomous Knowledge Discovery
  7. 2026Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation
  8. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning