DeepSeek unveils 'Super-agent' design to handle multiple tasks in parallel and improve efficiency
The DeepSeek logo is displayed on a smartphone screen, with the words “AI Agent” in the background. (Photo: VCG)
Chinese artificial intelligence (AI) company DeepSeek has unveiled a new system architecture called "Super-Agent," designed to enable AI agents to handle multiple tasks simultaneously, while operate continuously with less human intervention, as Chinese AI companies increasingly focus on making AI systems more autonomous and capable of handling complex work.
In an article published on Saturday, the DeepSeek Harness team said that as AI models become increasingly capable of completing individual tasks, human attention is emerging as a bottleneck to productivity. Most existing AI agents still operate through separate sessions, requiring users to switch between tasks and manually manage their context. According to the team, one person can keep track of only three to five active sessions at a time.
To address the limitations, DeepSeek proposed four major features for Super-agent: continuity, efficiency, proactivity and persistence. The proposed system would allow users to interact with the same agent across messaging and coding platforms, handle complex tasks in parallel, identify matters requiring attention without explicit instructions and remain operational over extended periods, including recovering from interruptions.
The design centers on a two-layer structure comprising a Router and multiple Workers. The Router manages user communication, maintains shared context and assigns tasks, while Workers carry out assignments independently and report their progress and results. Supported by event-driven operations, asynchronous interactions and an external monitoring mechanism known as Watchdog, the system aims to take over routine session management and coordination, allowing people to focus on higher-level decisions and reviewing results.
The latest design builds on DeepSeek's earlier work on AI agents. In August, the company released a developer preview of DeepSeek Harness, an open-source framework that enables AI models to use tools and execute tasks through a modular, plugin-based architecture, marking a significant step in the company's expansion from developing large AI models to building practical AI agent applications.
DeepSeek said that an internal Super-agent system is now running, helping reproduce and fix software problems, respond to code reviews and improve DeepSeek Harness itself. For example, when developers discuss a potential software bug in a group chat, the agent can identify the issue and try to reproduce it and find a solution in the background, even without being directly asked.
The team has made a research prototype publicly available, but noted that it is not an official DeepSeek product or production-ready software. The published version differs from the system used internally, and some features outlined in the article remain under development, according to the project's official GitHub repository.
DeepSeek's exploration comes as other Chinese technology companies push AI agents further into business operations.
On Thursday, Tencent said that its Agent Development Platform (ADP) allows enterprises to customize, manage and coordinate agents for customer service, marketing and operations. Tencent said a key challenge in enterprise adoption is shifting from improving model capabilities to connecting agents with existing business systems, data and workflows.
Alibaba Cloud is also expanding its infrastructure for autonomous AI agents. In July, it introduced AgentLoop and AgentTeams to help businesses monitor agent performance and coordinate multiple agents handling complex workflows. Together with its existing AgentRun platform, the tools support the development, deployment and management of enterprise-level AI applications.
These developments highlight a growing focus in China's AI industry on moving beyond individual tasks toward systems capable of coordinating complex work and improving productivity. However, DeepSeek acknowledged in the article that challenges remain, including scaling the system to handle growing workloads, maintaining long-term memory, enabling communication between different AI agents, and addressing security and privacy risks, particularly when cloud-based agents access local devices.