arXiv AI
Are LLM Agents Behaviorally Coherent? A Latent Profiling Approach for Social Simulation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 30
LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
arXiv:2411. 10109v3 Announce Type: replace Abstract: Machine learning can predict human behavior well when substantial structured data are available for well-defined outcomes.
arXiv Computation and Language
Aug 25
Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases
arXiv:2608.10503v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. T...
arXiv AI
Jun 2
Simulating Macroeconomic Expectations in Survey Experiments with LLM-based Economic Agents
arXiv:2505. 17648v5 Announce Type: replace-cross Abstract: We introduce a framework for simulating macroeconomic expectations in survey experiments using LLM-based economic agents (LLM Agents).
arXiv Computation and Language
Sep 11
The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies
The study audits 576 LLM-based social simulations from 350 papers using the PIMMUR framework, which evaluates agent profile, interaction, memory, minimal control, unawareness, and realism. Results show that PIMMUR principles are met more often than minimal control, unawareness, and realism, with frontier LLMs correctly identifying the underlying experiment in 65.2% of cases and half of prompts pre‑determining outcomes. Reproducing five experiments revealed that many reported collective phenomena disappear or reverse when PIMMUR principles are enforced, suggesting that apparent emergent behaviors may be methodological artifacts rather than genuine social dynamics.
arXiv AI
Oct 7
Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes
arXiv:2610.05828v2 Announce Type: replace Abstract: Large language models (LLMs) offer new opportunities for public opinion research by enabling early prediction of survey responses, potentially redu...
arXiv AI
Aug 11
Knowing You Is Everything: LLM Agents Achieve Near-Perfect Profile-Consistent Reaction Prediction in Social Media Simulation
arXiv:2608. 07498v1 Announce Type: cross Abstract: Autonomous AI agents in social media present concrete risks to democratic discourse and platform governance, while also offering tools for pre-deployment recommender system testing.