Search papers, labs, and topics across Lattice.
The paper introduces Guardian, a decision-support system for missing-child investigations that leverages a three-layer predictive architecture. This architecture combines a Markov chain model for spatiotemporal risk prediction, reinforcement learning to generate search plans, and an LLM for post-hoc validation of these plans. A synthetic case study demonstrates the system's ability to generate interpretable priors for search planning across 24/48/72-hour horizons, highlighting sensitivity, failure modes, and tradeoffs.
LLMs can provide quality assurance for reinforcement learning-based search plans in high-stakes missing-child investigations, improving the reliability of AI-driven decision support.
The first 72 hours of a missing-child investigation are critical for successful recovery. However, law enforcement agencies often face fragmented, unstructured data and a lack of dynamic, geospatial predictive tools. Our system, Guardian, provides an end-to-end decision-support system for missing-child investigation and early search planning. It converts heterogeneous, unstructured case documents into a schema-aligned spatiotemporal representation, enriches cases with geocoding and transportation context, and provides probabilistic search products spanning 0-72 hours. In this paper, we present an overview of Guardian as well as a detailed description of a three-layer predictive component of the system. The first layer is a Markov chain, a sparse, interpretable model with transitions incorporating road accessibility costs, seclusion preferences, and corridor bias with separate day/night parameterizations. The Markov chain's output prediction distributions are then transformed into operationally useful search plans by the second layer's reinforcement learning. Finally, the third layer's LLM performs post hoc validation of layer 2 search plans prior to their release. Using a synthetic but realistic case study, we report quantitative outputs across 24/48/72-hour horizons and analyze sensitivity, failure modes, and tradeoffs. Results show that the proposed predictive system with the three-layer architecture produces interpretable priors for zone optimization and human review.