Research

Paper

AI LLM March 05, 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

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.

Metadata

arXiv ID: 2603.05240
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-05
Fetched: 2026-03-06 14:20

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05240v1</id>\n    <title>GCAgent: Enhancing Group Chat Communication through Dialogue Agents System</title>\n    <updated>2026-03-05T14:55:57Z</updated>\n    <link href='https://arxiv.org/abs/2603.05240v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05240v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-05T14:55:57Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Zijie Meng</name>\n    </author>\n    <author>\n      <name>Zheyong Xie</name>\n    </author>\n    <author>\n      <name>Zheyu Ye</name>\n    </author>\n    <author>\n      <name>Chonggang Lu</name>\n    </author>\n    <author>\n      <name>Zuozhu Liu</name>\n    </author>\n    <author>\n      <name>Zihan Niu</name>\n    </author>\n    <author>\n      <name>Yao Hu</name>\n    </author>\n    <author>\n      <name>Shaosheng Cao</name>\n    </author>\n  </entry>"
}