{"ID":2867867,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18063","arxiv_id":"2509.18063","title":"ARK-V1: An LLM-Agent for Knowledge Graph Question Answering Requiring Commonsense Reasoning","abstract":"Large Language Models (LLMs) show strong reasoning abilities but rely on internalized knowledge that is often insufficient, outdated, or incorrect when trying to answer a question that requires specific domain knowledge. Knowledge Graphs (KGs) provide structured external knowledge, yet their complexity and multi-hop reasoning requirements make integration challenging. We present ARK-V1, a simple KG-agent that iteratively explores graphs to answer natural language queries. We evaluate several not fine-tuned state-of-the art LLMs as backbones for ARK-V1 on the CoLoTa dataset, which requires both KG-based and commonsense reasoning over long-tail entities. ARK-V1 achieves substantially higher conditional accuracies than Chain-of-Thought baselines, and larger backbone models show a clear trend toward better coverage, correctness, and stability.","short_abstract":"Large Language Models (LLMs) show strong reasoning abilities but rely on internalized knowledge that is often insufficient, outdated, or incorrect when trying to answer a question that requires specific domain knowledge. Knowledge Graphs (KGs) provide structured external knowledge, yet their complexity and multi-hop re...","url_abs":"https://arxiv.org/abs/2509.18063","url_pdf":"https://arxiv.org/pdf/2509.18063v1","authors":"[\"Jan-Felix Klein\",\"Lars Ohnemus\"]","published":"2025-09-22T17:40:05Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}