Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Agentic Group Decision Support

2025-07-01

AI Summary

Existing group recommendation systems face practical deployment challenges due to overreliance on static preference aggregation and failure to model authentic group communication dynamics. This paper proposes a generative-AI-driven, agent-based paradigm for group decision support, wherein AI agents actively engage in multi-turn group dialogues to enable dynamic intent recognition, context-aware negotiation, and consensus facilitation—replacing conventional one-shot recommendations. Methodologically, we design a human-AI collaborative framework leveraging large language models (e.g., ChatGPT) to support real-time collective intent modeling, personalized suggestion generation, and interactive decision assistance. Our approach significantly enhances the naturalness, interpretability, and user engagement of the recommendation process, bridging the gap between theoretical group recommendation models and real-world social scenarios. It establishes an extensible technical pathway and principled design guidelines for next-generation collaborative decision-making systems.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Multiagent Systems: Mechanism Design

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

More than twenty-five years ago, first ideas were developed on how to design a system that can provide recommendations to groups of users instead of individual users. Since then, a rich variety of algorithmic proposals were published, e.g., on how to acquire individual preferences, how to aggregate them, and how to generate recommendations for groups of users. However, despite the rich literature on the topic, barely any examples of real-world group recommender systems can be found. This lets us question common assumptions in academic research, in particular regarding communication processes in a group and how recommendation-supported decisions are made. In this essay, we argue that these common assumptions and corresponding system designs often may not match the needs or expectations of users. We thus call for a reorientation in this research area, leveraging the capabilities of modern Generative AI assistants like ChatGPT. Specifically, as one promising future direction, we envision group recommender systems to be systems where human group members interact in a chat and an AI-based group recommendation agent assists the decision-making process in an agentic way. Ultimately, this shall lead to a more natural group decision-making environment and finally to wider adoption of group recommendation systems in practice.

Problem

• Redesign group recommender systems using Generative AI
• Address mismatch between academic assumptions and user needs
• Enhance group decision-making with AI-assisted chat interactions

Innovation

• Leveraging Generative AI for group recommendations
• AI agent assists group decision-making interactively
• Enhancing natural group decision-making with chat