mlsanityData to 7 Oct 2026

SPeCtrum: A Grounded Framework for Multidimensional Identity Representation in LLM-Based Agent

arXiv 2502.08599 ↗First posted 12 Feb 2025cs.CLcited by 8

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Existing methods for simulating individual identities often oversimplify human complexity, which may lead to incomplete or flattened representations. To address this, we introduce SPeCtrum, a grounded framework for constructing authentic LLM agent personas by incorporating an individual's multidimensional self-concept. SPeCtrum integrates three core components: Social Identity (S), Personal Identity (P), and Personal Life Context (C), each contributing distinct yet interconnected aspects of identity. To evaluate SPeCtrum's effectiveness in identity representation, we conducted automated and human evaluations. Automated evaluations using popular drama characters showed that Personal Life Context (C)-derived from short essays on preferences and daily routines-modeled characters' identities more effectively than Social Identity (S) and Personal Identity (P) alone and performed comparably to the full SPC combination. In contrast, human evaluations involving real-world individuals found that the full SPC combination provided a more comprehensive self-concept representation than C alone. Our findings suggest that while C alone may suffice for basic identity simulation, integrating S, P, and C enhances the authenticity and accuracy of real-world identity representation. Overall, SPeCtrum offers a structured approach for simulating individuals in LLM agents, enabling more personalized human-AI interactions and improving the realism of simulation-based behavioral studies.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 20 of its 56 references that are in the map. First posted on arXiv 12 Feb 2025.

Builds on

20 of 56 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Can Large Language Model Agents Simulate Human Trust Behavior?7 Feb
  2. 2023Simulating Opinion Dynamics with Networks of LLM-based Agents16 Nov
  3. 2023Character-LLM: A Trainable Agent for Role-Playing16 Oct
  4. 2023User Behavior Simulation with Large Language Model based Agents5 Jun

Other references · 16

  1. 2023Whose Opinions Do Language Models Reflect?cited by 759
  2. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  3. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  4. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
  5. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 300
  6. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 229
  7. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  8. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMscited by 191
  9. 2022Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?cited by 89
  10. 2023From Sparse to Dense: GPT-4 Summarization with Chain of Density Promptingcited by 52
  11. 2024From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake Newscited by 51
  12. 2024Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Workscited by 38
4 more
  1. 2022Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterancescited by 32
  2. 2024Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humanscited by 31
  3. 2023MPCHAT: Towards Multimodal Persona-Grounded Conversationcited by 24
  4. 2023An Empathy-Based Sandbox Approach to Bridge the Privacy Gap among Attitudes, Goals, Knowledge, and Behaviorscited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2026The Need for a Socially-Grounded Persona Framework for User Simulationcited by 14
  2. 2025Simulating Society Requires Simulating Thoughtcited by 12
  3. 2026Knowing But Not Doing: Convergent Morality and Divergent Action in LLMscited by 6
  4. 2025A Review of Incorporating Psychological Theories in LLMscited by 5
  5. 2025Feed-O-Meter: Investigating AI-Generated Mentee Personas as Interactive Agents for Scaffolding Design Feedback Practicecited by 0
  6. 2026InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspectioncited by 0
  7. 2026The Librarian Who Refused to Code: Model-Dependent Identity Enactment in LLM Code Generationcited by 0
  8. 2026Personalizing LLM Agent Memory Using Biometricscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans
  2. 2026Distributed Human Identity: AI-Enabled Multi-Existence Through Cognitive Replication and Robotic Embodiments
  3. 2024Identity-Driven Hierarchical Role-Playing Agents
  4. 2025Population-Aligned Persona Generation for LLM-based Social Simulation
  5. 2025ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agents
  6. 2024Agentic Society: Merging skeleton from real world and texture from Large Language Model
  7. 2026STEMMA: An Adversarial Multi-Agent Framework for Evaluating Self-Identity Consistency in LLMs
  8. 2026MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations