Prospector is a compact model that learns to traverse a domain knowledge graph step by step, calling a small set of tools to build context and produce a chain of evidence that can be verified against the graph. Trained on a semiconductor‑manufacturing knowledge graph, it matches or surpasses off‑the‑shelf models that use the same graph and tools, and it also transfers to unseen graphs in bio‑inspired materials, PFAS, and materials properties. Running on a single GPU, Prospector is faster and cheaper than hosted services while keeping proprietary data on the owner’s hardware.
arXiv:2602.02518v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many knowledge sources on the Web, such as sc...
arXiv:2610.35598v1 Announce Type: new Abstract: Knowledge graphs (KGs) provide reliable external knowledge for multi-hop factual reasoning with large language models (LLMs), yet most KGs in real-worl...
arXiv:2605. 26874v2 Announce Type: replace-cross Abstract: LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores.
HyGRAIL is a framework for discovering scientific hypotheses in incomplete knowledge graphs by combining a graph neural network (GNN) triage with large language model (LLM) review. The GNN scores candidate hypotheses and routes only ambiguous cases to the LLM, which receives structured evidence from the graph converted into natural language. Experiments on MatKG show HyGRAIL achieves the highest F1 score, improves over baselines, and cuts LLM calls by over 54%.
Scientific knowledge graphs organize entities and relations extracted from scientific literature, but they remain inherently incomplete. Missing typed links in such graphs can therefore represent plau...
arXiv:2603. 14147v2 Announce Type: replace Abstract: The generative artificial intelligence (AI) ecosystem is undergoing rapid transformations that threaten its sustainability.
arXiv:2606. 13669v1 Announce Type: new Abstract: Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration.
arXiv:2610.06650v2 Announce Type: replace Abstract: Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right en...
GraphNIAH is a new benchmark for long‑context reasoning that uses real citation relationships among scientific papers published after a model’s knowledge cutoff. It automatically samples subgraphs of the citation graph and turns each into a long‑context QA example with a verifiable answer, avoiding synthetic data, dataset reuse, manual annotation, and trivial reasoning steps. Evaluation of eight large language models shows that accuracy drops sharply as reasoning depth increases, indicating that current models often fail to fully explore citation relationships even when all necessary facts are present.
arXiv:2609.27297v2 Announce Type: replace Abstract: Agentic science envisions many autonomous agents investigating concurrently while building on a shared, evolving body of scientific knowledge. This...
GraphCert introduces a method to bootstrap graph reasoning agents by generating graph‑grounded question‑answer pairs and certifying the supporting evidence. The approach uses a Bootstrapped Graph Quizzer to produce QA pairs, then executes and semantically curates the evidence into certified rubrics that guide reward‑based training of a Graph Solver. Experiments on five GRBENCH domains show GraphCert outperforms larger LLM agents and demonstrates robust policy transfer across heterogeneous graphs.
The paper introduces the Large Knowledge Model (LKM), a scientific knowledge infrastructure that converts research literature into shared, computationally accessible reasoning graphs. LKM aligns questions, claims, and reasoning chains across papers, creating a Scientific Reasoning Landscape with Question, Workflow, and Evidence views. The system enhances scientific search, evidence‑grounded QA, and research planning, achieving notable accuracy gains on ChemBench, PubMedQA, and SciBench.