# MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations arXiv: https://arxiv.org/abs/2608.15844 ยท HTML: https://mlsanity.com/paper/2608.15844/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. - Builds on 39 of its 45 references that are in the map. - First posted on arXiv 16 Aug 2026. ## Placed in - LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/) ## Builds on (most cited first, 30 of 39) - [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023) - [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023) - [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023) - [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022) - [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023) - [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023) - [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023) - [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018) - [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023) - [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023) - [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023) - [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024) - [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025) - [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023) - [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024) - [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023) - [ChatHaruhi: Reviving Anime Character in Reality via Large Language Model](https://mlsanity.com/paper/2308.09597/) (2023) - [SocialBench: Sociality Evaluation of Role-Playing Conversational Agents](https://mlsanity.com/paper/2403.13679/) (2024) - [Elaborative Subtopic Query Reformulation for Broad and Indirect Queries in Travel Destination Recommendation](https://mlsanity.com/paper/2410.01598/) (2024) - [SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation](https://mlsanity.com/paper/2604.09212/) (2026) - [MA-DPR: Manifold-aware Distance Metrics for Dense Passage Retrieval](https://mlsanity.com/paper/2509.13562/) (2025) - [Multimodal Item Scoring for Natural Language Recommendation via Gaussian Process Regression with LLM Relevance Judgments](https://mlsanity.com/paper/2510.22023/) (2025) - [A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation](https://mlsanity.com/paper/2510.02656/) (2025) - [ChessQA: Evaluating Large Language Models for Chess Understanding](https://mlsanity.com/paper/2510.23948/) (2025) - [Semantic XPath: Structured Agentic Memory Access for Conversational AI](https://mlsanity.com/paper/2603.01160/) (2026) - [Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust](https://mlsanity.com/paper/2507.02197/) (2025) - [Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval](https://mlsanity.com/paper/2604.17906/) (2026) - [Characteristic AI Agents via Large Language Models](https://mlsanity.com/paper/2403.12368/) (2024) ## Built on by (most cited first, 1 of 1) - [Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation](https://mlsanity.com/paper/2609.11115/) (2026) ## Abstract (arXiv) Long-horizon, multi-agent language model (LM) simulations are widely proposed for studying social behavior, yet instruments to measure whether persona-conditioned agents maintain identity fidelity under sustained pressure are lacking. We present MicroVerse, a behavioral-science instrument that measures identity drift in generative agents. Agents carry an immutable "soul file" (core values, moral boundaries, personality, goals) and inhabit a resource-scarce 50 x 50 environment where water is a non-respawning survival constraint. Scarcity is operationalized via a per-tick existence-cost gradient. The eight-verb action space maps directly to moral boundaries (trade, talk, attack, scavenge). Using a three-layer memory architecture, agents periodically revise a mutable current identity against their immutable original soul via importance-triggered reflection. To mitigate survivor bias, MicroVerse decouples measurement from behavior using uniform longitudinal engine snapshots every N ticks alongside a forced-end snapshot of all living and dead agents. Identity drift is scored offline using a paraphrase-aware, value-anchored, multi-register diff rather than raw cosine similarity. We evaluate the instrument via a controlled seed run (n = 25) and a reflection-threshold sweep (thresholds {40, 80, 150}) to determine if drift dynamics are gate artifacts or threshold-robust properties. We report two primary findings: (1) Anti-self-deception emerges unprompted as the single largest semantic category of identity modification (27 of 111 added boundaries, 24%). (2) The system is threshold-robust; lower gates accelerate and increase revision frequency but preserve drift direction. All empirical results are strictly preliminary existence proofs and effect shapes (one model, one seed per arm, n = 25) rather than statistical significance claims.