# Researchers release PsyBer-Agent, a psychology-driven recommender system simulator

Digest AI · Research · published 2026-10-14T04:00:00Z

Canonical: https://digestai.news/story/researchers-release-psyber-agent-a-psychology-driven-recommender-syste

## Summary

Researchers introduced PsyBer-Agent, a new simulator designed to improve recommender systems by modeling user dynamics like fatigue and shifting preferences. The system uses a Psy-Engine with three evolving latent states per user, calibrated against real interaction logs via Unbalanced Gromov-Wasserstein optimal transport. This avoids heavy fine-tuning of the underlying LLM while maintaining behavioral realism over long interactions.

The framework includes WebSim and the PsyBer Benchmark, testing seven recommender backbones across multimodal scenarios. PsyBer-Agent outperforms prompt-only simulators in behavioral fidelity and stability, handling up to 5 million concurrent simulation tasks. Code and platforms are available on 4open.science.

## Key points

- PsyBer-Agent simulates user dynamics like fatigue and preference shifts via a Psy-Engine with three latent states
- Calibration uses Unbalanced Gromov-Wasserstein optimal transport to align simulated behavior with real logs
- Supports 5M concurrent tasks and outperforms prompt-only simulators in behavioral fidelity tests

## Why it matters

A more realistic simulator could accelerate testing of recommender systems before deployment, reducing reliance on real-world user data.

## Sources

1. [PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems](https://arxiv.org/abs/2610.13989) (arXiv cs.CL, 2026-10-14, primary source)

## Cite

Digest AI, "Researchers release PsyBer-Agent, a psychology-driven recommender system simulator", 14 October 2026, https://digestai.news/story/researchers-release-psyber-agent-a-psychology-driven-recommender-syste

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-release-psyber-agent-a-psychology-driven-recommender-syste.json