HEAS: Hierarchical Evolutionary Agent Simulation Framework for Cross-Scale Modeling and Multi-Objective Search

2025-08-21

AI Summary

This paper addresses the challenges of unifying cross-scale modeling with multi-objective optimization and poor reproducibility. We propose the Hierarchical Evolutionary Agent Simulation (HEA-Sim) framework, which employs a lightweight process-flow architecture to explicitly model cross-scale couplings and decouple mechanistic modeling from scheduling policies. HEA-Sim integrates hierarchical agent-based simulation, multi-objective evolutionary optimization, and competition-based evaluation using customizable scoring or voting rules, enabling unified workflows for forward simulation, parameter optimization, and system comparison. Implemented in Python, it provides both a command-line interface and a compact API. Built-in features include tensorized policy-parameter manipulation, persistent storage for seeds/logs/hall-of-fame archives, and Pareto-front visualization tools. These capabilities significantly reduce boilerplate “glue” code, enhance model reusability, auditability, and cross-study comparability.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Hierarchical Evolutionary Agent Simulation (HEAS) is a Python framework that unifies layered agent-based modeling with evolutionary optimization and tournament evaluation in a single, reproducible workflow. HEAS represents models as hierarchies of lightweight processes ("streams") scheduled in deterministic layers that read and write a shared context, making cross-scale couplings explicit and auditable. A compact API and CLI-simulate, optimize, evaluate-expose single- and multi-objective evolution, PyTorch policy integration via parameter flattening/unflattening, and general tournament tooling with user-defined scoring and voting rules. The framework standardizes evaluation through uniform per-step and episode metrics, persists seeds, logbooks, and hall-of-fame archives, and provides plotting helpers for traces, Pareto fronts, and comparative outcomes, reducing glue code and improving comparability across studies. HEAS emphasizes separation of mechanism from orchestration, allowing exogenous drivers, endogenous agents, and aggregators to be composed and swapped without refactoring, while the same model can be used for forward simulation, optimization, or systematic comparison. We illustrate usage with two compact examples-an ecological system and an enterprise decision-making setting. HEAS offers a practical foundation for cross-disciplinary, multi-level inquiry, yielding reliable, reproducible results.

Problem

• Unifying agent-based modeling with evolutionary optimization for cross-scale simulations
• Enabling multi-objective search and policy integration in reproducible workflows
• Standardizing evaluation metrics to reduce glue code and improve comparability

Innovation

• Hierarchical agent-based modeling with evolutionary optimization
• Deterministic layered processes with shared context
• PyTorch integration and multi-objective tournament evaluation