Are LLM Agents Behaviorally Coherent? A Latent Profiling Approach for Social Simulation
cs.AI, cs.CL, cs.LG
Submitted: 2025-09-03
Updated: 2026-10-11
Terminology
Sources
- LLM Social Simulations Are a Promising Research Method
- Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models
- The Llama 3 Herd of Models
- Scaling Synthetic Data Creation with 1,000,000,000 Personas
- War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars
- Large Language Models Pass the Turing Test
- Measuring and Controlling Instruction (In)Stability in Language Model Dialogs
- Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification
- From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents
- LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
- Cultural evolution in populations of Large Language Models
- Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysis
- Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities
- Gemma 3 Technical Report
- From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems