AgentCTG: Harnessing Multi-Agent Collaboration for Fine-Grained Precise Control in Text Generation

2025-09-17

AI Summary

Addressing challenges in controlled text generation (CTG)—namely, fine-grained conditional control, domain-knowledge preservation, and scalability for real-world deployment—this paper proposes AgentCTG, a multi-agent collaborative framework. AgentCTG models rewriting tasks via role-driven decomposition, incorporates an automatic prompt generation module, and employs a context-aware textual regulation mechanism to jointly control semantics, style, and domain-specific knowledge. Its key innovation lies in adapting multi-agent collaboration to CTG: agents are assigned distinct, semantically grounded roles and responsibilities, and a dedicated knowledge retention strategy ensures domain fidelity and expertise. Empirically, AgentCTG achieves state-of-the-art performance across multiple benchmark datasets. In an online navigation application, it significantly improves role-playing consistency and user immersion, demonstrating strong efficacy and practicality in real-world deployment. (149 words)

Technology Category

• Multiagent Systems: Teamwork
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Although significant progress has been made in many tasks within the field of Natural Language Processing (NLP), Controlled Text Generation (CTG) continues to face numerous challenges, particularly in achieving fine-grained conditional control over generation. Additionally, in real scenario and online applications, cost considerations, scalability, domain knowledge learning and more precise control are required, presenting more challenge for CTG. This paper introduces a novel and scalable framework, AgentCTG, which aims to enhance precise and complex control over the text generation by simulating the control and regulation mechanisms in multi-agent workflows. We explore various collaboration methods among different agents and introduce an auto-prompt module to further enhance the generation effectiveness. AgentCTG achieves state-of-the-art results on multiple public datasets. To validate its effectiveness in practical applications, we propose a new challenging Character-Driven Rewriting task, which aims to convert the original text into new text that conform to specific character profiles and simultaneously preserve the domain knowledge. When applied to online navigation with role-playing, our approach significantly enhances the driving experience through improved content delivery. By optimizing the generation of contextually relevant text, we enable a more immersive interaction within online communities, fostering greater personalization and user engagement.

Problem

• Achieving fine-grained conditional control in text generation
• Addressing cost and scalability in controlled text generation
• Enhancing domain knowledge preservation and character-driven rewriting

Innovation

• Multi-agent collaboration for fine-grained control
• Auto-prompt module enhancing generation effectiveness
• Character-driven rewriting preserving domain knowledge