PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems

arXiv:2610.13989 · cs.CL, cs.IR, cs.LG · Submitted 2026-09-26 · Read on arXiv

cs.CL, cs.IR, cs.LG

Submitted: 2026-09-26

Updated: 2026-09-26

Sources

UserSimCRS v2: Simulation-Based Evaluation for Conversational Recommender Systems
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
Contextualizing Recommendation Explanations with LLMs: A User Study
The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes
LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems
VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Generative Agents and Expectations: Do LLMs Align with Heterogeneous Agent Models?
Membership Inference Attacks on In-Context Examples in LLM-based Recommender Systems
Session-based Recommendations with Recurrent Neural Networks
Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancy
Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
RecSim: A Configurable Simulation Platform for Recommender Systems
Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
RecoWorld: Building Simulated Environments for Agentic Recommender Systems
Exploring Backdoor Attack and Defense for LLM-empowered Recommendations
A Survey on LLM-powered Agents for Recommender Systems
BPR: Bayesian Personalized Ranking from Implicit Feedback
Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations
LLMs as Strategic Actors: Behavioral Alignment, Risk Calibration, and Argumentation Framing in Geopolitical Simulations

Related papers