GCAgent: Enhancing Group Chat Communication through Dialogue Agents System

Zijie Meng; Zheyong Xie; Zheyu Ye; Chonggang Lu; Zuozhu Liu; Zihan Niu; Yao Hu; Shaosheng Cao

cs.AIMar 5, 2026

GCAgent: Enhancing Group Chat Communication through Dialogue Agents System

Authors: Zijie Meng, Zheyong Xie, Zheyu Ye, Chonggang Lu, Zuozhu Liu, Zihan Niu, Yao Hu, Shaosheng Cao

Organizations: Xiaohongshu Inc. Shanghai, China · University of Science and Technology of China, Hefei, China

Abstract

As a key form in online social platforms, group chat is a popular space for interest exchange or problem-solving, but its effectiveness is often hindered by inactivity and management challenges. While recent large language models (LLMs) have powered impressive one-to-one conversational agents, their seamlessly integration into multi-participant conversations remains unexplored. To address this gap, we introduce GCAgent, an LLM-driven system for enhancing group chats communication with both entertainment- and utility-oriented dialogue agents. The system comprises three tightly integrated modules: Agent Builder, which customizes agents to align with users' interests; Dialogue Manager, which coordinates dialogue states and manage agent invocations; and Interface Plugins, which reduce interaction barriers by three distinct tools. Through extensive experiment, GCAgent achieved an average score of 4.68 across various criteria and was preferred in 51.04% of cases compared to its base model. Additionally, in real-world deployments over 350 days, it increased message volume by 28.80%, significantly improving group activity and engagement. Overall, this work presents a practical blueprint for extending LLM-based dialogue agent from one-party chats to multi-party group scenarios.

Figures & tables

Figure 1. The overview of our GCAgent system.

Panel of Figure 2 — Figure 2. The user interface of GCAgent. And a brief live demonstration is available on YouTube .

Models	Direct scoring
Models	Correctness	Consistency	Fairness	Engagement	Average
Qwen	4.18	4.33	4.90	4.27	4.42
GCAgent	4.40	4.79	4.94	4.59	4.68

Table 1. Results of direct scoring in offline evaluation.

GCAgent vs Qwen	Win	Tie	Lose
GCAgent vs Qwen	51.04%	29.57%	19.39%

Table 2. Results of indirect comparison in offline evaluation.

Metric	Group Activity	New Group Creation	Message Readership	Message Volumes
Improvement (%)	+4.02	+6.27	+11.07	+28.80

Table 3. Online evaluation results. Unique user views is used to assess message readership, and amount to others.

Figure 3. Role distribution of top 20 most popular agents.

Conversational Agents

Conversational agents are AI systems that interact with people through multi-turn dialogue to answer questions, provide support, or complete tasks.

See all 287 papers

GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant
Mar 1, 2026Zhuokang Shen, Yifan Wang, Hanyu Chen +6Conversational Agents LLM Inference Efficiency
East China Normal University Shanghai, China · University of Nottingham Ningbo Ningbo, China · Xiamen University Xiamen, China
GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
Mar 20, 2026Hongjiang Chen, Xin Zheng, Yixin Liu +7Multi-Agent Communication Topology Multi-Agent Communication
School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China · School of Computing Technologies, RMIT University, Melbourne, Australia · School of Information and Communication Technology, Griffith University, Goldcoast, Australia
GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
May 14, 2026Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang +3Conversational Memory LLM Agent Evaluation
UC Santa Barbara · Microsoft

Mar 1, 2026J/K move · Enter open · S save

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

Zhuokang Shen, Yifan Wang, Hanyu Chen, Yunhang Shen+5

East China Normal University Shanghai, China · University of Nottingham Ningbo Ningbo, China · Xiamen University Xiamen, China

Conversational Agents LLM Inference Efficiency Privacy-Preserving Language Models

Open paper AskPDF arXiv

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 chat interactions, where agents require more proactive and accurate intervention under complex, evolving contexts. Existing approaches typically rely on LLMs for both intervention reasoning and response 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 an edge-cloud model collaboration architecture to decouple intervention timing from response generation, enabling efficient and accurate decision-making while preserving user privacy through on-device processing of sensitive information. The framework also supports multimodal inputs, including memes, images, videos, and voice messages.To support evaluation of timing accuracy and response quality, 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. We evaluate a range of models on MUIR, spanning from open-source to proprietary variants, including both LLMs and their smaller counterparts. Extensive experiments demonstrate that GroupGPT generates 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 the token usage by up to 3 times compared to baselines, while providing privacy sanitization of user messages before cloud transmission. Code is available at: https://github.com/Eliot-Shen/GroupGPT .

Abstract

Conversational Agents

Explore similar work

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

GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems

GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations