GroupGPT：面向多用户聊天助手的令牌高效与隐私保护型智能体框架

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

March 1, 2026

作者: Zhuokang Shen, Yifan Wang, Hanyu Chen, Wenxuan Huang, Shaohui Lin

cs.AI

摘要

近年來大型語言模型（LLM）的突破顯著提升了聊天機器人的能力。然而現有系統多專注於單用戶場景，難以適應多人群組聊天的複雜需求——在動態演變的對話情境中，智能體需具備更主動且精準的介入能力。傳統方法通常依賴單一LLM同時進行推理與生成，導致令牌消耗量大、可擴展性受限，並存在潛在隱私風險。為解決這些挑戰，我們提出GroupGPT：一種面向多用戶聊天場景的令牌高效型隱私保護智能體框架。該框架採用「小模型-大模型」協作架構，將介入時機判斷與回應生成解耦，實現高效精準的決策機制，同時支持表情包、圖像、視頻及語音訊息等多模態輸入。我們進一步構建MUIR基準數據集，包含2,500段帶有介入標籤與推理依據的標注群聊片段，用於評估介入時機準確性與回應質量。在MUIR上對從大型語言模型到輕量模型的對比實驗表明，GroupGPT能產生時機恰當的精準回應，在LLM評估中獲得4.72/5.0的平均分，並在多元群組場景中獲得用戶積極反饋。相較基準方法，GroupGPT可降低最高3倍的令牌消耗，且在雲端傳輸前對用戶訊息進行隱私過濾。項目代碼已開源於：https://github.com/Eliot-Shen/GroupGPT。

English

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 more 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. To address these challenges, we propose GroupGPT, a token-efficient and privacy-preserving agentic framework for multi-user chat assistant. GroupGPT adopts a small-large model collaborative architecture to decouple intervention timing from response generation, enabling efficient and accurate decision-making. The framework also supports multimodal inputs, including memes, images, videos, and voice messages. We further introduce MUIR, a benchmark dataset for multi-user chat assistant intervention reasoning. MUIR contains 2,500 annotated group chat segments with intervention labels and rationales, supporting evaluation of timing accuracy and response quality. We evaluate a range of models on MUIR, from large language models to smaller counterparts. Extensive experiments demonstrate that GroupGPT produces accurate and well-timed responses, achieving an average score of 4.72/5.0 in LLM-based evaluation, and is well received by users across diverse group chat scenarios. Moreover, GroupGPT reduces token usage by up to 3 times compared to baseline methods, while providing privacy sanitization of user messages before cloud transmission. Code is available at: https://github.com/Eliot-Shen/GroupGPT .