LONG AI
Home › Blog › DeepSeek Open-Sources a Super-Agent Arch

DeepSeek Open-Sources a Super-Agent Architecture: Task Time Halved, AI Manages Itself

Category:行业资讯 · 9 min read · 2026-11-02

This column aggregates the latest large-model releases and open-source drops from the past one to two days, cross-checked against official announcements and multiple media outlets. Performance figures distinguish between vendor claims and independently verified third-party results; anything not yet replicated is clearly marked. Illustrations are original.

Central control hub coordinating multiple robots illustration

Headline: DeepSeek open-sources a Super-agent architecture (evening of Oct 31)

DeepSeek's team published "Super-agent Design Exploration: Toward More Autonomous Agent Systems" and open-sourced a runnable prototype on GitHub (dsh-superagent-prototype, MIT). It's not a new product - it's an engineering blueprint answering a very practical question: AI can finish a single task without supervision now, but one person can only follow 3-5 active sessions at once - the multi-task ceiling is shifting from "model capability" to "human attention."

DeepSeek's answer borrows decades of systems engineering:

The numbers: task time nearly halved (vendor's own)

In a simulated collaboration of ~300 messages and 20 work requests (vendor-described experiment, synthetic, simplified, 5 runs per config, marked "preliminary"): Super-agent median completion 12.4 min, p95 15.7 min; the traditional single-session approach was 20.4 / 29.5 min - nearly twice at p95. Subscriptions saved the Router ~37% token overhead; batching cut per-decision inference from 6.4s to 1.6s. The team also admitted the other side of the ledger: more cached-token reads than single-session.

DeepSeek says an internal instance built on this has been running in daily development - reproducing and fixing issues, code-review responses, and iterating the Harness itself. Take: while others race to make models "a bit smarter," DeepSeek is investing in "system-layer scheduling." If this route pans out, agent products morph from "a chat box" to "a colleague that lives in the background."

Other releases (3)

Model / ProductDateTypeHighlights
SenseNova Loop-9B-Preview (SenseTime, open source, Apache 2.0)10-30 / 11-1Multimodal LLM (recurrent)Pitched as "deepen compute, don't stack parameters": 32 layers holding 9B, the middle 24 layers run twice on shared weights, one forward pass equals 56 layers (~14.6B inference), with an mHC dual-stream residual to stabilize signal. Vendor-claimed office and agent tasks beat Qwen3.5-27B (WorkBuddy Bench 66.89, BIRD-Dev 71.38) but lose Terminal-Bench 2.1 (40.45 vs Qwen3.6-27B's 47.19); all self-reported, no tech report yet. 262K training context.
Pika H3 Flex (Pika, open weights + API)10-29 / 11-1Audio-video joint generationA post-trained "iteration specialist" on MiniMax H3: two LoRA adapters (text/first-last-frame FL2VA, multimodal-reference Ref2VA with up to 12 references), distilled to 6 denoising steps (teacher 50), native 480P/768P up to 15s with synced stereo; the API can split audio into dialogue/score/SFX/foley/ambience tracks. Vendor: #8 on DesignArena text-to-video, #1 open video model; "15s 768p in 7s" is a controlled-benchmark claim, unreplicated.
PixelUMM (NVIDIA x Waterloo, open source)9-29 / 11-1Unified multimodal (understand + generate)Kills the "standard dual-encoder": no ViT, no VAE - images split into 16x16 patches, video into 4-frame spatiotemporal blocks, one linear projection feeds raw pixels into a Qwen3-8B backbone, understanding and generation share attention. Top unified-model video understanding (MVBench 70.53), VBench 83.24, GenEval 0.77 - the paper says "comparable" to baselines, not crushing. Code and weights open. Honest weakness: MMMU 41.67, well behind specialist VLMs; grid artifacts on smooth regions at high CFG.

Industry news

The trend in one line

Today's keyword is "digging deeper." DeepSeek touches the agent's system layer, SenseTime touches Transformer depth, NVIDIA touches the multimodal encoder - after the parameter race cooled, everyone is betting on the same thing: smarter structure rather than bigger scale, wringing more output out of each unit of compute.

(Data from official announcements and public reports, 2026-11-02; vendor claims and third-party results are marked separately, with unverified items noted in the text. Model capability affects selection, but actual pricing follows the model plaza in real time.)

相关文章

GPT-6.2 Cuts Prices 20%: What the AI Price War Means

GPT-6.2 cuts list prices 20%, yet platform discounts run deeper: gpt-6-astra trades at under 1% of list. What this week's AI price war means for buyer

What Is Prompt Caching? How Cache Tokens Cut API Bills

Prompt caching stores a repeated prompt prefix and bills cache reads at 5-12% of normal input. Real prices, hit conditions, and how to cut your API bi

All 12 Claude Models Compared: Price and Best Use

Twelve Claude versions are on sale. The newest opus-5-5 costs $8.91 a month; the oldest opus-4-6 costs $49.50. Full table and a pick for each workload

Which AI Model Writes Code Best? Speed and Price Tested

gpt-5.6-terra and deepseek-v4.1-flash win on price and reliability; gemini-3.8-flash is fastest. Effective prices, measured speed, and a three-tier pi

One API Key, Every Model: How to Integrate a Multi-Model Marketplace

Point your base URL at the platform and one key covers all 138 on-sale models across 51 vendors, in both OpenAI and Anthropic request formats. Copy-pa