A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations

Researchers have developed Guardian, an AI system using multiple large language models (LLMs) to assist in missing-person investigations during the critical first 72 hours. The system employs a consensus-driven pipeline that coordinates specialized LLM models for information extraction and processing, with fine-tuning using QLoRA methodology.

• →Guardian is an end-to-end AI system specifically designed for missing-child investigation and early search planning.
• →The system uses multiple specialized LLM models coordinated through a consensus engine that resolves disagreements between model outputs.
• →The pipeline emphasizes conservative, auditable use of LLMs as structured extractors rather than unconstrained decision makers.
• →QLoRA-based fine-tuning is employed using curated datasets to strengthen the system's performance.
• →The design focuses on the critical first 72 hours when missing-person recovery efforts are most effective.