为大模型多智能体系统设计动态监管机制，提升运行可靠性
Position: Towards a Responsible LLM-empowered Multi-Agent Systems
- 引入动态人工干预机制，实时调节智能体交互
- 解决大模型输出不可控导致的系统风险累积问题
- 适合关注AI系统安全与可控性的研究者和开发者
Agent AI 和大语言模型驱动的多智能体系统（LLM-MAS）的兴起，凸显了负责任且可靠系统运行的重要性。LangChain 和检索增强生成等工具拓展了大模型能力，通过增强知识检索与推理，实现了更深层次的多智能体集成。然而，这些进展也带来了严峻挑战：大模型智能体存在固有的不可预测性，其输出不确定性在交互中会不断累积，威胁系统稳定性。为应对这些风险，必须采用以人类为中心的设计理念，结合主动的动态监管机制。该机制通过促进智能体间连贯沟通与有效系统治理，超越传统被动监督，使多智能体系统能更高效地达成预期目标。
原文摘要 · Abstract (English)
The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS) has underscored the need for responsible and dependable system operation. Tools like LangChain and Retrieval-Augmented Generation have expanded LLM capabilities, enabling deeper integration into MAS through enhanced knowledge retrieval and reasoning. However, these advancements introduce critical challenges: LLM agents exhibit inherent unpredictability, and uncertainties in their outputs can compound across interactions, threatening system stability. To address these risks, a human-centered design approach with active dynamic moderation is essential. Such an approach enhances traditional passive oversight by facilitating coherent inter-agent communication and effective system governance, allowing MAS to achieve desired outcomes more efficiently.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。