arXiv AI
Aug 25
Walking on the DARKSIDE
arXiv:2608.23370v1 Announce Type: new Abstract: Large Language Models (LLMs) recognise patterns but do not natively track the path of exclusions that a coherent discourse demands. When an input rests...
What Does an Ontology Catch? Curated, LLM-Generated and Data-Derived Ontologies as Checkers of LLM Agents over Knowledge Graphs
The paper investigates how different types of ontologies—curated, LLM-generated, and data-derived—serve as checkers for large language model agents answering questions over knowledge graphs. By evaluating these ontologies as prompt context, as checkers, or both, across both open-weight and proprietary agents on public and a large private graph, the study quantifies the trade-offs between errors caught and false alarms. It finds that curated ontologies can flag more correct answers than other sources but are only marginally more precise than random, and that combining sources or providing specific feedback offers limited benefits.
Related stories
arXiv AI
Sep 10
Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version)
The paper proposes a four‑dimensional formal framework—Semantic Expressivity, Agentic Discoverability, Task‑Relative Grounding, and Epistemic Trust Scope—to extend current KG metadata standards (VoID and DCAT). It introduces the Agentic Affordance Profile (AAP), a semantic layer that enables agents to select, compose, and diagnose failures in knowledge graphs at planning time. A scholarly‑search example illustrates the framework and outlines a five‑point research agenda for scaling AAP‑based affordance matching.
arXiv AI
Sep 10
OntoKG-EQ: A provenance-grounded, competency-question-governed knowledge graph for auditable analyst querying
arXiv:2609.08869v1 Announce Type: cross Abstract: Analysts in emerging equity markets keep answering the same questions. Did fundamentals match the market's response? How does the local currency co-m...
arXiv AI
Aug 18
Quipu: A Governed Bitemporal Knowledge Graph Store
arXiv:2608. 16813v1 Announce Type: new Abstract: Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: accept writes now and clean later, keep one time axis or none, treat every writer's facts as equally trustworthy, and leave governance to dashboards and middleware.
arXiv AI
Jul 23
Do Data Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval
arXiv:2605. 28787v2 Announce Type: replace-cross Abstract: In the era of autonomous agents, machine-actionable data is critical for data-driven workflows.
arXiv AI
Sep 1
From Extraction to Governed Memory: Multi-Agent Knowledge Graph Construction with Domain-Expert Review
arXiv:2608.28642v1 Announce Type: new Abstract: Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with little record of who owns a fact, why it was admit...
Hugging Face Trending Papers
Aug 26
Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems
Answer accuracy is an insufficient reliability signal for LLM data agents. In structured-data tasks, a benchmark-correct answer can be produced by an invalid trace. This paper introduces Trace Integri...
arXiv AI
Aug 24
Auditable by Construction: An Ontology-Driven Framework for Trustworthy LLM Analytics in Enterprise Finance
The paper introduces the Knowledge-Driven Analytics Framework (KDAF), an ontology‑driven approach for large language model analytics in enterprise finance that prioritizes auditability. KDAF constructs knowledge systems through six iterative stages and retrieves evidence via Context‑Aware Relevance Propagation (CARP), ensuring each fact includes its relationship type, confidence, and source lineage. Evaluation on FinanceBench shows that while retrieval improves accuracy marginally, KDAF significantly outperforms other methods in citation traceability and provenance completeness, demonstrating that auditability is the key advantage of ontology‑grounded retrieval.
arXiv Computation and Language
Aug 27
Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems
The paper argues that answer accuracy alone is insufficient for evaluating large language model (LLM) data agents, especially in structured-data tasks where a correct answer can be produced by an invalid trace. It introduces Trace Integrity as a reliability criterion that ensures the computation behind an answer is explicit, executable, schema-valid, operator-faithful, replayable, answer-consistent, and auditable. The authors operationalize this concept with execution contracts and present the CAIT (Correct Answer / Invalid Trace) Rate to quantify how often answer-only evaluations mistakenly reward unsupported outputs, demonstrating that accuracy, trace validity, and silent-failure risk are distinct signals.
arXiv AI
Oct 28
OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning
OA‑RAG is an agent that combines formal ontology reasoning with large language model (LLM) reasoning to produce more faithful answers. For each response it lists the ontology observations used as evidence and assigns a grounding level—entailed, supported, related, or unrelated—to indicate the strength of that evidence. On benchmarks from three large ontologies and six real‑world medical QA tasks, OA‑RAG outperforms other ontology‑fine‑tuned and popular RAG methods, especially on reasoning‑intensive questions, and its grounding levels correlate with higher accuracy.
arXiv AI
Jul 3
ContextNest: Verifiable Context Governance for Autonomous AI Agent
arXiv:2607. 02116v1 Announce Type: new Abstract: Autonomous AI agents increasingly depend on external knowledge stores, yet most retrieval pipelines provide relevance without durable guarantees of provenance, version identity, integrity, traceability, or point-in-time reconstruction.
arXiv AI
Oct 26
Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It Retrieves
The paper presents a knowledge layer that reorganizes enterprise Retrieval-Augmented Generation (RAG) for multi‑agent systems by placing an ontology at the artifact level rather than on extracted entities. Using a seven‑agent reverse‑engineering pipeline, the authors processed 241 repositories across 18 services to generate thousands of artifacts that capture scope, journeys, rules, and acceptance criteria, each tagged with provenance metadata. The resulting self‑describing catalog, sparse metadata registry, and navigation hypergraph enable queries to resolve to artifact identifiers, thereby structurally disambiguating near‑identical rules and improving retrieval accuracy. The system was built in under a week and helped root‑cause over 100 production defects and attribute 35 release regressions to specific rules and services.