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

Abstract:AIvilization v0 is a publicly deployed large-scale artificial society that couples a resource-constrained sandbox with a unified LLM-agent architecture, aiming to sustain long-horizon autonomy while remaining executable under a rapidly changing environment. To mitigate the tension between goal stability and reactive correctness, keeping long-horizon objectives on course while each action remains valid in a fast-changing shared world, 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 instead of 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. In a large-scale public deployment with tens of thousands of agents, high-frequency transactions from the platform's mature phase reveal stable markets that reproduce key stylized facts of real economies and structured wealth stratification driven by education and access constraints. At the agent level, portraits evolve coherently over long horizons, and human steering is associated with measurably larger short-horizon profile updates. Controlled ablation experiments complement the deployment evidence, showing that our agent architecture is robust in multi-objective, long-horizon settings.

v2: major revision. Agent architecture and environment consolidated into self-contained sections; new problem-setting section formalizing the asynchronous event model; evaluation reorganized by experiment with results reported alongside each protocol; added action-simulator audit, and human-steering analyses; other sections rewritten

Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)

arXiv:2602.10429 [cs.MA]

(or arXiv:2602.10429v2 [cs.MA] for this version)