A systems-level dissection of aging and longevity mechanisms powered by an evidence-routed AI knowledge graph

Aging is a complex biological process influenced by numerous molecular and cellular factors. A systems-level understanding of these mechanisms is essential for identifying key regulatory processes and prioritizing effective interventions. Here, we present a comprehensive dissection of aging and longevity mechanisms powered by an evidence-routed AI-based knowledge graph, HALDxAI. By integrating 445,435 aging- and longevity-related publications with 19 authoritative biomedical databases, we construct a unified Aging Knowledge Graph (Aging-KG) utilizing ontology-aligned normalization and large language model (LLM)-driven extraction. HALDxAI employs a multi-agent retrieval system that anchors reasoning to verifiable sentence-level evidence, achieving lower hallucination on domain-specific benchmarks. Crucially, network analyses of the Aging-KG revealed the topological landscape of the "aging-longevity axis," identifying key cross-domain regulators such as TP53, mTOR, and SIRT1 that function as bridge nodes between degenerative and pro-longevity pathways. In addition, an inflammaging-focused case study demonstrates the capacity of HALDxAI to decompose modular structures and position anti-aging interventions. Overall, HALDxAI mitigates knowledge fragmentation and provides a scalable platform for mechanism discovery and intervention prioritization in aging and longevity research.