DeepSeek Open-Sources Super-agent Prototype for Persistent, Autonomous Agent Workflows
刚刚，DeepSeek重磅开源：Agent底座架构！
- Who
- DeepSeek
- What
- shared the Super-agent architecture and initial evaluation results
- Quote
DeepSeek团队在文章中提到，根据他们的观察，一个人通常只能同时跟进3到5个活跃Session。
What happened
DeepSeek shared its Super-agent architecture and open-source prototype for coordinating ongoing tasks across platforms through a Router and multiple Workers. QbitAI reports that preliminary simulations involving about 300 messages and 20 work requests produced a median task completion time of 12.4 minutes and a 95th-percentile time of 15.7 minutes. The design includes event filtering, direct routing, and a Watchdog for recovery; its asynchronous ReAct loop is implemented in DeepSeek Harness but is not enabled by default.
Why it matters
The architecture offers a transferable approach to coordinating concurrent agent tasks through shared context and direct event routing, with preliminary experiments illustrating the associated latency and token costs.
Read next
See the full storyDeepSeek Shares Super-agent Architecture, Open-Source Prototype and Initial EvaluationThe story so far
DeepSeek shared its Super-agent architecture and an open-source prototype designed to coordinate ongoing tasks across platforms, with preliminary simulations showing a median task completion time of 12.4 minutes, according to QbitAI. The design uses a Router and multiple Workers, with event filtering, direct routing and a Watchdog for recovery. Its asynchronous ReAct loop is implemented in DeepSeek Harness but is not enabled by default. QbitAI reported that the simulations involved about 300 messages and 20 work requests, with a 95th-percentile task completion time of 15.7 minutes.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-10-31