Discussing Intelligence
AI Agent – The Year of the Intelligent Agent: From Technical Core to Application Landscape
The China Industrial Internet Research Institute has released a new platform for AI-empowered new industrial supply and demand matching service (hereinafter referred to as the “supply and demand matching service platform”), which gathers high-quality supply and demand resources from various industries. A special column on discussing intelligence has been established to interpret hot topics in artificial intelligence technology, analyze trends in industrial applications, and promote typical solutions empowered by artificial intelligence for new industrialization.
The year 2025 is widely defined by the industry as the “Year of the Intelligent Agent.” In this year, intelligent agent technology is expected to experience explosive growth, rapidly transitioning from cutting-edge concepts in laboratories to various industries, gradually emerging in the industrial sector: a certain automotive company, in collaboration with multiple research institutes, successfully constructed 12 business intelligent agents covering areas such as intelligent interviews, power battery trial production, architecture fault diagnosis, and standard review, expected to save over 30,000 hours of labor annually; a logistics company built a data governance intelligent agent that, through automated data governance and report generation, released 80% of the manual costs of report production, saving the company over 20 million yuan in labor costs. These real solutions from the supply and demand matching service platform indicate that intelligent agent technology has already taken root in industrial scenarios, becoming a new engine driving the intelligent transformation of the manufacturing industry.
Unlike general large models, intelligent agents can not only understand human instructions but also perceive the environment, plan actions, and call tools to autonomously achieve deep adaptation to industrial scenarios. Through continuous interaction with real scenarios, intelligent agents accumulate experience and optimize strategies, ultimately achieving a leap from “passive response” to “active execution.” From office process automation to deep interaction in intelligent customer service, and to autonomous operation and maintenance in complex industrial environments, intelligent agents demonstrate extraordinary potential in the industrial field.
Today, let us explore what intelligent agents are and how they can bring about change in industrial scenarios.
What are Intelligent Agents Based on Large Models?
Intelligent Agents (AI Agent) are AI systems characterized by autonomy, reactivity, proactivity, and social capabilities, driven by large models, and include key components such as Planning, Memory, and Tools usage [2].
▷Planning: Responsible for breaking down large tasks into sub-tasks, optimizing solution steps through self-reflection and thinking chains, improving the quality of output content.
▷Memory: Responsible for storing information; short-term memory refers to context learning related content, while long-term memory is used for retrieving external databases to complete complex tasks.
▷Tools: Responsible for calling external tools, such as application programming interfaces (APIs), to obtain additional information.
Overview of AI Agent Structure (Image Source: Reference [2])
In industrial scenarios, intelligent agents perceive environmental signals through sensors, rely on large models to complete business data searches, plan industrial actions, call external tools, and ultimately make decision reasoning to execute industrial operations. At the same time, these intelligent agents possess natural language interaction capabilities, enabling collaboration and competition among multiple agents, applicable in real scenarios such as product drawing design and operation and maintenance decision-making.
Application Landscape
Intelligent Agent Technology Drives Innovation Across the Industrial Chain
In the wave of technological iteration, intelligent agents based on large models have sparked a wave of process reconstruction and model innovation across multiple industries. We will focus on data governance and intelligent operation and maintenance, exploring how intelligent agents use technological power to break industry dilemmas.
Platform Solution One:
Building Intelligent Operation Solutions for Data Assets
Industry Pain Points: In industries such as manufacturing and finance, which are highly dependent on data, data governance has long faced the constraints of “manual shackles.” In traditional models, data analysis, metric calculation, and report generation rely entirely on manual operations, which are time-consuming and labor-intensive; the complex structure of data assets makes it difficult to support rapid decision-making, becoming a “stumbling block” for enterprises to respond to market changes.
Intelligent Agents Breakthrough: In response to these pain points, intelligent agents serving data governance have emerged, covering processes such as data production management, retrieval analysis, and value pushing to create a self-operating “data knowledge base” for enterprises.
In the data production management phase, intelligent agents act as “data asset managers,” autonomously constructing an enterprise data knowledge base based on a metric system. They leverage large models and retrieval-augmented generation (RAG) technology to project relationships between business metadata and technical metadata, weaving data without needing to rebuild existing data warehouses, accurately identifying effective data assets and completing semantic encapsulation. The woven data includes core elements such as metrics, field names, tags, dimension values, physical tables, and their relational history, laying the foundation for constructing a data knowledge graph and achieving a self-closed loop of “data production – governance – sedimentation.”
Data Production Management and Retrieval Analysis (Image Source: Platform Solution)
In the data retrieval analysis phase, intelligent agents transform into “decision analysts,” allowing data queries and analyses to break free from “technical barriers.” Users only need to input their requirements in natural language, and the intelligent agent can complete semantic understanding and instruction breakdown through large models, accurately finding matching asset projections in the data knowledge graph using RAG technology. Subsequently, the intelligent agent automatically generates multiple structured query statements (SQL), constructing a complete analytical thought chain, providing clear analytical opinions like a “professional consultant.”
In the data value pushing phase, intelligent agents become “data salespeople,” transforming business models from “passive queries” to “active pushes.” Relying on large model technology, they organize the contextual logic of data assets through data catalogs, standardization, and contextualization, subsequently intelligently sensing the user’s specific industry scenario. Without the need for user inquiries, intelligent agents can insightfully understand user needs like a “personal advisor,” creating real-time analysis tasks and actively pushing core information to users, allowing business personnel to obtain immediate decision-making basis without mastering SQL or industry knowledge.
Implementation Results: Intelligent agents, through automatically generating SQL and reports with large models, significantly reduce manual intervention in the data governance process, shorten decision-making cycles, and noticeably improve business response speeds. In data retrieval analysis, intelligent agents have served over 8,000 users, with total usage exceeding 320,000 times; in data value pushing, the market business valuation of related intelligent agents has approached 100 billion yuan, proving the value of intelligent agent technology in digital governance.
Platform Solution Two:
Establishing a Digital Operation Team with Multi-Agent Collaboration
Industry Pain Points: As digital transformation deepens, enterprise IT environments are becoming increasingly complex, and operational maintenance demands are surging, leading to continuous pressure on human resources. The traditional “manual monitoring, passive response” operational maintenance model is no longer sustainable; how to use technology to liberate manpower and improve efficiency has become a challenge faced by enterprises in digital transformation.
Intelligent Agents Breakthrough: In the wave of digital reform, digital operation teams based on multi-agent collaboration have emerged. The core of this team consists of job intelligent agents and tool intelligent agents, which quickly generate various solutions through multi-agent collaboration, empowering and enhancing the efficiency of actual operational maintenance personnel, reshaping operational processes, and helping enterprises maintain a competitive edge in the wave of digital transformation.
Overall Framework of Operational Maintenance Intelligent Agents (Image Source: Platform Solution)
Job Intelligent Agents are the “professional backbone” of the team, trained using deep learning and professional knowledge graph technology to simulate the professional roles of operational maintenance positions. Whether it is network monitoring, system optimization, or fault diagnosis, each job intelligent agent is equipped with knowledge and experience in the corresponding field, capable of making professional judgments in complex scenarios that rival human experts.
Tool Intelligent Agents serve as the “bridge” connecting job intelligent agents with actual operational maintenance tools. This intelligent agent possesses basic functions for using tools while also understanding higher-level task objectives, autonomously deciding how to apply tools based on context, and proactively providing analytical suggestions, ensuring that technical tools genuinely serve operational maintenance goals.
Implementation Results: Through multi-agent collaboration, operational maintenance intelligent agents can autonomously complete most workflow processes, allowing operational maintenance personnel to efficiently handle massive amounts of operational maintenance information by focusing only on key aspects. Currently, this intelligent agent has successfully empowered 120,000 engineers, providing professional operational maintenance support for various manufacturing industries, helping enterprises establish a foothold in the digital wave.
Conclusion
Although there are still many issues in industrial scenarios, such as data silos, lack of reliability verification, and incomplete standard systems, the trend of intelligent agent technology taking root in industry has already formed. With the rapid implementation of large model technology in industrial scenarios and the gradual improvement of the multi-agent cross-process collaboration ecosystem, intelligent agents will become the core link connecting industrial digital twins with actual production, building a smarter and more efficient production environment for manufacturing enterprises. For enterprises and practitioners, grasping the evolution logic of intelligent agents and proactively laying out intelligent transformation of core processes will be key to seizing future competitive advantages.
END
more
｜Learn More
If you want to learn more about the specific applications, technical details, and latest research results of intelligent agent-related technologies in actual production, please visit the supply and demand matching service platform (https://www.ai-bridge.cn). There, you can find more in-depth content that supports the intelligent transformation and upgrading of the manufacturing industry.
Contact Person：
Mr. Liu
010-87901204
Mr. Chen
010-87901203
References:
[1] Xi Z, Chen W, Guo X, et al. The rise and potential of large language model based agents: A survey[J]. Science China Information Sciences, 2025, 68(2): 121101.
[2] WENG L. LLM-powered autonomous agents[EB/OL].[2023-06-23]. https://lilianweng.github.io/posts/2023-06-23-agent/.
Subscribe and Follow
The Jiangsu Provincial Industrial Internet Development Research Center (Jiangsu Branch of the China Industrial Internet Research Institute) is jointly built by the China Industrial Internet Research Institute, the Jiangsu Provincial Department of Industry and Information Technology, the Jiangsu Provincial Communications Administration, and the Suzhou Municipal People’s Government, aiming to lay out national strategic new infrastructure in Jiangsu Province and coordinate national strategic resources, establishing an important research institution that fully supports the innovative development of the industrial internet in Jiangsu Province.