AutoGen Driven Multi Agent Framework for Iterative Crime Data Analysis and Prediction
This work addresses scalable and privacy-preserving crime analysis for social science applications, though it appears incremental as an adaptation of AutoGen-style agents to a specific domain.
The paper tackles crime data analysis and prediction by introducing LUCID-MA, a multi-agent AI framework that collaboratively analyzes spatiotemporal patterns and forecasts trends, achieving self-improvement through 100 rounds of agent communication with minimal human input.
This paper introduces LUCID-MA (Learning and Understanding Crime through Dialogue of Multiple Agents), an innovative AI powered framework where multiple AI agents collaboratively analyze and understand crime data. Our system that consists of three core components: an analysis assistant that highlights spatiotemporal crime patterns; a feedback component that reviews and refines analytical results; and a prediction component that forecasts future crime trends. With a well-designed prompt and the LLaMA-2-13B-Chat-GPTQ model, it runs completely offline and allows the agents undergo self-improvement through 100 rounds of communication with less human interaction. A scoring function is incorporated to evaluate agent performance, providing visual plots to track learning progress. This work demonstrates the potential of AutoGen-style agents for autonomous, scalable, and iterative analysis in social science domains, maintaining data privacy through offline execution. It also showcases a computational model with emergent intelligence, where the system's global behavior emerges from the interactions of its agents. This emergent behavior manifests as enhanced individual agent performance, driven by collaborative dialogue between the LLM-based agents.