arXiv AI August 18, 2026 By Yuyang Zheng, Nan Li, Wenxia Deng, Lige Yan, Xiang Li, Si Chen

Valhalla: A Layered Knowledge-State and Service-Governance Framework for Long-Term Scientific Knowledge Work

arXiv:2608. 15193v1 Announce Type: cross Abstract: As large language model (LLM) agents are increasingly adopted in scientific research, external knowledge bases, knowledge graphs, and long-term memory have improved information retrieval and task continuity.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 12

Agents-K1: Towards Agent-native Knowledge Orchestration

arXiv:2606. 13669v1 Announce Type: new Abstract: Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration.

By Zongsheng Cao, Bihao Zhan, Jinxin Shi, Jiong Wang, Fangchen Yu, Zhijie Zhong, Zijie Guo, Tianshuo Peng, Zhuo Liu, Yi Xie, Xiang Zhuang, Yue Fan, Runmin Ma, Shiyang Feng, Xiangchao Yan, Anran Liu, Peng Ye, Wenlong Zhang, Shufei Zhang, Chunfeng Song, Fenghua Ling, Jie Zhou, Liang He, Bo Zhang, Lei Bai

llms agents multimodal

arXiv AI

Jul 7

Knowledge-Centric Information Systems

arXiv:2607. 02609v1 Announce Type: cross Abstract: For decades, data engineering has developed mature architectural principles for integrating, governing, validating, cataloging, and serving organizational data.

By Mariano Garralda-Barrio

llms agents data-engineering

arXiv Machine Learning

2d ago

AutoSchema: Live Schema Grounding for Agentic Text-to-Sparql over Heterogeneous Knowledge Graphs

arXiv:2608. 14228v1 Announce Type: new Abstract: Life science knowledge graphs make large collections of structured data available through SPARQL, but each resource uses its own schema, identifiers, and links.

By Yiming Zhang, Koji Tsuda

llms agents

arXiv AI

Jul 28

Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration

arXiv:2607. 24512v1 Announce Type: new Abstract: Mathematical models are central to formalizing research problems, yet their documentation often falls short of FAIR principles.

By Jan Range, Bj\"orn Schembera, Dominik G\"oddeke

llms rag agents safety

arXiv AI

Jul 24

From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics

arXiv:2607. 21327v1 Announce Type: cross Abstract: Bibliometric indicators - citation counts, h-indexes, co-authorship networks - have long anchored science, technology, and innovation (STI) analytics, yet suffer from temporal lag, semantic shallowness, and an inability to capture the non-linear dynamics of contemporary knowledge ecosystems.

By Muhsen Hammoud

llms safety

arXiv AI

Jul 2

The MMM Data Model -- A Normative Specification for Knowledge Interoperability in a Decentralisable Knowledge Commons

arXiv:2607. 00032v1 Announce Type: new Abstract: Many information systems are built around documents: self-contained units optimised for print production and linear reading.

By Mathilde Noual

Related stories

Agents-K1: Towards Agent-native Knowledge Orchestration

Knowledge-Centric Information Systems

AutoSchema: Live Schema Grounding for Agentic Text-to-Sparql over Heterogeneous Knowledge Graphs

Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration

From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics

The MMM Data Model -- A Normative Specification for Knowledge Interoperability in a Decentralisable Knowledge Commons