mlsanityData to 14 Oct 2026

Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications

arXiv 2511.02979 ↗First posted 4 Nov 2025cs.HC cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The design and application of LLM-based personas in AI companionship is a rapidly expanding but fragmented field, spanning from virtual emotional companions and game NPCs to embodied functional robots. This diversity in objectives, modality, and technical stacks creates an urgent need for a unified framework. To address this gap, this paper systematizes the field by proposing a Four-Quadrant Technical Taxonomy for AI companion applications. The framework is structured along two critical axes: Virtual vs. Embodied and Emotional Companionship vs. Functional Augmentation. Quadrant I (Virtual Companionship) explores virtual idols, romantic companions, and story characters, introducing a four-layer technical framework to analyze their challenges in maintaining long-term emotional consistency. Quadrant II (Functional Virtual Assistants) analyzes AI applications in work, gaming, and mental health, highlighting the shift from "feeling" to "thinking and acting" and pinpointing key technologies like enterprise RAG and on-device inference. Quadrants III & IV (Embodied Intelligence) shift from the virtual to the physical world, analyzing home robots and vertical-domain assistants, revealing core challenges in symbol grounding, data privacy, and ethical liability. This taxonomy provides not only a systematic map for researchers and developers to navigate the complex persona design space but also a basis for policymakers to identify and address the unique risks inherent in different application scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 110 references that are in the map. First posted on arXiv 4 Nov 2025.

Builds on

36 of 110 references.

References · 36

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  6. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  7. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  8. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 345
  9. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 338
  10. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 279
  11. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 175
  12. 2018The Design and Implementation of XiaoIce, an Empathetic Social Chatbotcited by 172
24 more
  1. 2024A Survey on Large Language Model-Based Game Agentscited by 112
  2. 2024The Dark Side of AI Companionship: A Taxonomy of Harmful Algorithmic Behaviors in Human-AI Relationshipscited by 62
  3. 2025Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agentscited by 62
  4. 2025Embodied AI Agents: Modeling the Worldcited by 61
  5. 2025Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learningcited by 27
  6. 2024TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Modelscited by 22
  7. 2025EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safetycited by 21
  8. 2025TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matchingcited by 19
  9. 2025Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counselingcited by 18
  10. 2024FACTS About Building Retrieval Augmented Generation-based Chatbotscited by 15
  11. 2024Unbounded: A Generative Infinite Game of Character Life Simulationcited by 14
  12. 2025Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLMcited by 9
  13. 2025Speculative End-Turn Detector for Efficient Speech Chatbot Assistantcited by 6
  14. 2025Multimodal Safety Evaluation in Generative Agent Social Simulationscited by 6
  15. 2024Advancing Conversational Psychotherapy: Integrating Privacy, Dual-Memory, and Domain Expertise with Large Language Modelscited by 5
  16. 2025SyncAnimation: A Real-Time End-to-End Framework for Audio-Driven Human Pose and Talking Head Animationcited by 5
  17. 2025LLM-Driven NPCs: Cross-Platform Dialogue System for Games and Social Platformscited by 5
  18. 2024Game Plot Design with an LLM-powered Assistant: An Empirical Study with Game Designerscited by 4
  19. 2024Leveraging Large Language Models for Active Merchant Non-player Characterscited by 4
  20. 2024Agentic AI-Driven Technical Troubleshooting for Enterprise Systems: A Novel Weighted Retrieval-Augmented Generation Paradigmcited by 4
  21. 2025From Documents to Dialogue: Building KG-RAG Enhanced AI Assistantscited by 3
  22. 2025Affective and Conversational Predictors of Re-Engagement in Human-Robot Interactions -- A Student-Centered Study with A Humanoid Social Robotcited by 3
  23. 2025DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignmentcited by 3
  24. 2025Continuous Learning Conversational AI: A Personalized Agent Framework via A2C Reinforcement Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Deco: Extending Cherished Physical Objects into AI Companion Agents through Dual Embodiment
  2. 2024The influence of persona and conversational task on social interactions with a LLM-controlled embodied conversational agent
  3. 2026ExpressionCueLens: A Cross-Cultural Analysis of Human-AI Companion Conversations on Social Media ↗
  4. 2026Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness
  5. 2026Distributed Human Identity: AI-Enabled Multi-Existence Through Cognitive Replication and Robotic Embodiments
  6. 2026Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling
  7. 2024Building Better AI Agents: A Provocation on the Utilisation of Persona in LLM-based Conversational Agents
  8. 2025Can LLMs Generate Behaviors for Embodied Virtual Agents Based on Personality Traits?