header-langage
简体中文
繁體中文
English
Tiếng Việt
한국어
日本語
ภาษาไทย
Türkçe
Scan to Download the APP
Partnered With:

DeepSeek launches new Agent architecture.

Beating AI News Flash, on the evening of October 31, the DeepSeek Harness team published a technical article titled "Super-agent Design Exploration: Toward a More Autonomous Agent System." DeepSeek stated that improvements in model capabilities have given rise to new application forms, and recently Personal Agents have begun to emerge in concentrated numbers. However, existing mainstream Agent designs still struggle to support this model at the scale of multi-tasking and team collaboration. The working mode of Agents still uses a single Session as the basic unit, and different Sessions are independent of one another. Under this design, the upper limit of a single task depends on model capability, while the upper limit of multi-tasking depends on human attention.


Through approaches such as a dual-layer architecture, event-driven design, asynchronous multi-channel interaction, separation of storage and computation, and an external Watchdog, the DeepSeek team has overcome these limitations. At the underlying level, the system takes over cumbersome session management and context synchronization, allowing humans to move further up from specific execution details to higher-level decision-making and acceptance. DeepSeek calls this Agent form and its system architecture Super-agent. The article mentions that at present, internal Super-agent instances built on this approach are already running continuously, participating daily in issue reproduction and fixes, code review responses, and iteration of DeepSeek Harness itself. (DeepSeek Harness Team)

举报 Correction/Report
RelatedRecommended
Price is $3 per million Tokens for input, $6 per million Tokens for output, and $0.025 per million Tokens for cache hit input.
DeepSeek: Hello Crypto, Big Hammer 80, Small Hammer 40, what hammer do you want?
DeepSeek V4-Flash Official Version API Launches Public Beta, Offering 1 Million Context, Pondering Mode, and Tool Invocation Capabilities at a Very Low Price.
Correction/Report
Submit
Add Library
Visible to myself only
Public
Save
Choose Library
Add Library
Cancel
Finish