GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant

ArXi:2603.01059v2 Announce Type: replace Recent advances in large language models (LLMs) have enabled increasingly capable chatbots. However, most existing systems focus on single-user settings and do not generalize well to multi-user group chats, where agents require proactive and accurate intervention under complex, evolving contexts. Existing approaches typically rely on LLMs for both reasoning and generation, leading to high token consumption, limited scalability, and potential privacy risks.