Argonaut: Interactive Visual Exploration for Distributed Optimization

2026-07-30

AI Summary

This work addresses the limited visibility into inter-agent dependencies and the evolution of global objectives in distributed discrete choice optimization within decentralized environments. To bridge this gap, the paper introduces a lightweight, containerized interactive optimization dashboard that, for the first time, integrates system construction, algorithm execution, and analysis into a closed-loop human-in-the-loop workflow. The system supports dynamic configuration of multi-agent systems, decision spaces, and multiple optimization backends, featuring a Node.js frontend coupled with an extensible Java/Python backend to enable parallel algorithm execution and real-time parameter tuning. Evaluated on real-world datasets—scaling up to 5,600 agents and solution spaces exceeding one million configurations—the framework achieves sub-30-second runtimes in representative scenarios (200 agents, 100 decision attributes), substantially enhancing the interpretability and interactive efficiency of distributed optimization.

Abstract

Distributed discrete-choice optimization in decentralized settings is often hard to explore and navigate: disentangling what other agents choose, how their choices are interdependent, and how they collectively reach a global objective quickly becomes intractable as the system scales. The major limitation is observability of the search process. Existing methods are largely centralized and offer limited support, visualizing only the final solution or providing algorithm backends over a fixed dataset, so how a solution is reached stays a black box. We present Argonaut, a lightweight, containerized optimization dashboard that enables interactive, visual exploration of the entire search process for multi-agent discrete-choice optimization in decentralized settings. Users upload datasets, construct agents and options, modify the decision space and its parameters on the fly, and run multiple algorithm backends to inspect how each configuration shapes local agent decisions and the resulting global objective. By uniting system construction, optimization, and analysis in one interactive loop, the first of its kind, Argonaut makes distributed discrete-choice optimization a human-in-the-loop process rather than a one-shot, black-box computation. We evaluate Argonaut on real-world household-electricity, shared-mobility, and sensor-data-exchange datasets scaling to 5600 agents and up to 1M solutions under brute force. Built on a Node.js interface with extensible Java and Python optimization backends, it maintains a typical runtime of 200 agents over 100 decision attributes in under 30 seconds.

Problem

• distributed optimization
• discrete-choice optimization
• decentralized systems
• observability
• multi-agent systems

Innovation

• interactive visualization
• distributed optimization
• multi-agent systems
• discrete-choice optimization
• human-in-the-loop