PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation

arXiv:2610.14570v1 Announce Type: new Abstract: Large language models (LLMs) support social simulation, but faithfully reproducing real users requires grounding both structured platform decisions and language in sparse, noisy behavioral evidence. We introduce PsyMemBehav, which maps psychology-informed profiles and retrieved memories to target-first platform behavior through two-level identity-to-action reasoning. To support this approach with comprehensive behavioral traces, we construct a dataset PsyMemBehav-bench from 5.57M observed behaviors of 5,862 real users (approximately 950 per user)

This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.