Related papers: On Generative Agents in Recommendation

Evaluating and iterating upon recommender systems is crucial, yet traditional A/B testing is resource-intensive, and offline methods struggle with dynamic user-platform interactions. While agent-based simulation is promising, existing…

Sequential recommendation aims to predict a user's next action in large-scale recommender systems. While traditional methods often suffer from insufficient information interaction, recent generative recommendation models partially address…

Designing and evaluating personalized and proactive assistant agents remains challenging due to the time, cost, and ethical concerns associated with human-in-the-loop experimentation. Existing Human-Computer Interaction (HCI) methods often…

In the rapidly evolving field of digital libraries, the development of large language models (LLMs) has opened up new possibilities for simulating user behavior. This innovation addresses the longstanding challenge in digital library…

Recent advancements in Natural Language Processing (NLP) have led to the development of NLP-based recommender systems that have shown superior performance. However, current models commonly treat items as mere IDs and adopt discriminative…

Large language models (LLMs) are increasingly integrated into recommender systems, motivating recent interest in agentic and reasoning-based recommendation. However, most existing approaches still rely on fixed workflows, applying the same…

Recommender systems are central to online services, enabling users to navigate through massive amounts of content across various domains. However, their evaluation remains challenging due to the disconnect between offline metrics and online…

Large language models (LLMs) are rapidly evolving from passive engines of text generation into agentic entities that can plan, remember, invoke external tools, and co-operate with one another. This perspective paper investigates how such…

Retrieval-Augmented Generation (RAG) has shown promise in enhancing recommendation systems by incorporating external context into large language model prompts. However, existing RAG-based approaches often rely on static retrieval heuristics…

Evaluating recommender systems remains challenging due to the gap between offline metrics and real user behavior, as well as the scarcity of interaction data. Recent work explores large language model (LLM) agents as synthetic users, yet…

In recommender systems, online A/B testing is a crucial method for evaluating the performance of different models. However, conducting online A/B testing often presents significant challenges, including substantial economic costs, user…

Recommender models excel at providing domain-specific item recommendations by leveraging extensive user behavior data. Despite their ability to act as lightweight domain experts, they struggle to perform versatile tasks such as providing…

In recent years, recommendation systems have evolved from providing a single list of recommendations to offering a comprehensive suite of topic focused services. To better accomplish this task, conversational recommendation systems (CRS)…

User simulators can rapidly generate a large volume of timely user behavior data, providing a testing platform for reinforcement learning-based recommender systems, thus accelerating their iteration and optimization. However, prevalent user…

Understanding human behavior and society is a central focus in social sciences, with the rise of generative social science marking a significant paradigmatic shift. By leveraging bottom-up simulations, it replaces costly and logistically…

Conversational recommender systems (CRS) enhance user experience through multi-turn interactions, yet evaluating CRS remains challenging. User simulators can provide comprehensive evaluations through interactions with CRS, but building…

Recent advances in large language models (LLMs) have enabled agent-based recommendation systems with strong semantic understanding and flexible reasoning capabilities. While LLM-based agents deployed in the cloud offer powerful…

Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies often rely on simplistic heuristics, require access to…

Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative…

We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can learn from errors without impacting real users. RecoWorld…