Temporal-Aware User Behaviour Simulation with Large Language Models for Recommender Systems

2025-09-20

AI Summary

Existing LLM-based recommendation systems predominantly rely on static user profiles, neglecting the temporal evolution of user interests and thereby yielding inaccurate behavioral simulations. To address this, we propose the first temporal-aware dynamic user behavior simulator, which jointly models sequential behavioral patterns and time-sensitive dynamics through three core components: (1) a dynamic user profile updating mechanism, (2) temporal-enhanced prompt engineering, and (3) an adaptive feedback aggregation strategy. Evaluated on real-world interaction data, our method significantly improves alignment between simulated and ground-truth user behaviors—e.g., achieving a 12.3% gain in Recall@10—at both individual and population levels. These results empirically validate the critical role of explicit temporal modeling in enhancing agent fidelity. This work establishes a novel, interpretable, and evolvable user agent paradigm for LLM-driven recommender systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Large Language Models (LLMs) demonstrate human-like capabilities in language understanding, reasoning, and generation, driving interest in using LLM-based agents to simulate human feedback in recommender systems. However, most existing approaches rely on static user profiling, neglecting the temporal and dynamic nature of user interests. This limitation stems from a disconnect between language modelling and behaviour modelling, which constrains the capacity of agents to represent sequential patterns. To address this challenge, we propose a Dynamic Temporal-aware Agent-based simulator for Recommender Systems, DyTA4Rec, which enables agents to model and utilise evolving user behaviour based on historical interactions. DyTA4Rec features a dynamic updater for real-time profile refinement, temporal-enhanced prompting for sequential context, and self-adaptive aggregation for coherent feedback. Experimental results at group and individual levels show that DyTA4Rec significantly improves the alignment between simulated and actual user behaviour by modelling dynamic characteristics and enhancing temporal awareness in LLM-based agents.

Problem

• Simulating temporal dynamics of user behavior in recommender systems
• Addressing static user profiling limitations in LLM-based agents
• Bridging the disconnect between language and behavior modeling

Innovation

• Dynamic temporal-aware agent modeling user behavior
• Real-time profile refinement with dynamic updater
• Temporal-enhanced prompting for sequential context