AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles

TL;DR

AIvilization v0 is a large-scale artificial society simulation integrating a unified agent architecture, adaptive profiles, and hierarchical planning to enable long-term autonomy, realistic economic behaviors, and human-in-the-loop control.

Contribution

This work introduces a comprehensive agent architecture with hierarchical planning and adaptive profiles for large-scale social simulation, enabling realistic long-term behaviors and human interaction.

Findings

Stable markets with stylized facts like heavy-tailed returns

Structured wealth stratification driven by education and access

Full architecture outperforms simplified planners in long-horizon tasks

Abstract

AIvilization v0 is a publicly deployed large-scale artificial society that couples a resource-constrained sandbox economy with a unified LLM-agent architecture, aiming to sustain long-horizon autonomy while remaining executable under rapidly changing environment. To mitigate the tension between goal stability and reactive correctness, we introduce (i) a hierarchical branch-thinking planner that decomposes life goals into parallel objective branches and uses simulation-guided validation plus tiered re-planning to ensure feasibility; (ii) an adaptive agent profile with dual-process memory that separates short-term execution traces from long-term semantic consolidation, enabling persistent yet evolving identity; and (iii) a human-in-the-loop steering interface that injects long-horizon objectives and short commands at appropriate abstraction levels, with effects propagated through memory rather than brittle prompt overrides. The environment integrates physiological survival costs, non-substitutable multi-tier production, an AMM-based price mechanism, and a gated education-occupation system. Using high-frequency transactions from the platforms mature phase, we find stable markets that reproduce key stylized facts (heavy-tailed returns and volatility clustering) and produce structured wealth stratification driven by education and access constraints. Ablations show simplified planners can match performance on narrow tasks, while the full architecture is more robust under multi-objective, long-horizon settings, supporting delayed investment and sustained exploration.