Agents-K1: New System for Converting Scientific Papers into Knowledge Graphs for AI Agents
Researchers have introduced Agents-K1, an end-to-end pipeline that transforms raw scientific documents into structured knowledge graphs for use by AI agents. The system integrates a multimodal parser, a 4-billion-parameter information-extraction model trained with reinforcement learning, and a unified agent interface for web search and graph retrieval. The work addresses a gap in LLM-based research agents, which have historically reduced papers to abstracts and flat citation links, losing critical scientific detail needed for multi-hop reasoning.
Agents-K1 is a newly proposed knowledge orchestration framework designed to overcome limitations in how current large language model (LLM)-based research agents process scientific literature. Rather than reducing papers to abstracts or simple citation edges, the pipeline extracts entities, claims, evidence, mechanisms, and methodological lineages from full documents, including multimodal content. The system comprises three integrated components: a five-module multimodal parser, a 4B-parameter information-extraction backbone trained using Group Relative Policy Optimization (GRPO) with rule-based rewards, and a command-line agent interface called graphanything CLI that unifies web search, multimodal graph retrieval, and cross-document traversal. Using this pipeline, the team processed 2.46 million scientific papers across six subject areas to construct Scholar-KG, a large-scale scientific knowledge graph, of which a one-million-paper subset is being publicly released. Experiments reported by the authors indicate that Agents-K1 achieves strong performance on scientific information extraction, knowledge graph construction, and multi-hop scientific reasoning tasks. The pipeline is also described as extensible to general-domain corpora and schema-conformant data synthesis.
What's missing
The paper does not report human evaluation of knowledge graph quality or factual accuracy of extracted claims. Scalability costs, computational requirements, and potential error propagation across the pipeline's three components are not discussed. The coverage and representativeness of the six subject areas in Scholar-KG are not specified.
What different sources said
- arXiv cs.AICenter
Agents-K1: Towards Agent-native Knowledge Orchestration
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.