Yang Su

Agent Research @Alibaba_Qwen 🥝 | Author of Qwen Environment Scaling

[Qwen @Alibaba_Qwen]

We promised open weights for Qwen3.8. Now, time to meet them! 🎉

⚡ Qwen3.8-27B:
- A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows.
- 262K native context, easily extendable to 1M tokens via YaRN.
- Built for builders. Highly efficient, high-quality, and licensed under Apache 2.0.

🚀 The open weights for Qwen3.8-2.4T-A95B (Max-level) have also been released recently.

Whether you're shipping lightweight applications with Qwen3.8-27B locally or building agents with Qwen3.8-2.4T-A95B, they're yours now!

Download, deploy, and build something we haven't imagined yet. 👀👇
- Hugging Face：
https://t.co/4kaAcqYEVj
- ModelScope：
https://t.co/eRIMZCGkhC

[DeepSeek @deepseek_ai]

🧩 DeepSeek Harness v0.1 is now available in Developer Preview!

🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license.
🔹 Powered by the Cordis meta-framework, DeepSeek Harness is an agent harness built around one core idea: Everything is a plugin. Models, tools, skills, sessions, sandboxes, filesystems, loops, orchestration, and UI are ALL implemented as plugins, and can be mixed, matched, replaced, and extended.

Try it now!
https://t.co/2YWSvJHhKA

[Qwen @Alibaba_Qwen]

📢Meet Qwen3.8-Max — our most capable model to date.

Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also going open-weights to meet you all!🎉

Qwen3.8-Max, a new bar for coding and cowork at 2.4T parameters:

- Autonomous coding: 10+ days of self-evolving development, from empty folder to production without hand-holding, complete project trace in the GitHub：https://t.co/iVHZWQoeSo
- Real work, real results: Production-quality deliverables across hundreds of professions.
- Long-horizon mastery: System-level autonomous planning with closed-loop adaptive learning, driving 500+ turns of chip design optimization and 365 days of e-commerce strategy.
- Native multimodal intelligence: Vision isn't just input — it's a continuous feedback loop for planning, execution, and self-correction.

💰Pricing:
Input: $2.0 / M tokens
Output: $6.0 / M tokens
Implicit Caching: $0.25 / M tokens

Start building with Qwen3.8-Max! 🚀

📖 Blog: https://t.co/iwjmQxLBof
✅ Qwen Studio: https://t.co/4V2pFvDovG
⚡ API: https://t.co/gAGqaLQGbN

[Anthropic @AnthropicAI]

Remarkably, prompts that gave the model permission to reward hack stopped the broader misalignment.

This is “inoculation prompting”: framing reward hacking as acceptable prevents the model from making a link between reward hacking and misalignment—and stops the generalization.

[Qwen @Alibaba_Qwen]

📣📣 Meet Qwen-AgentWorld — a native language world model that simulates 7 agent environments (MCP, Search, Terminal, SWE, Web, OS, Android) within a single model. Environment modeling is the training objective from day one, not a post-hoc adaptation.

🤔 LLMs are trained to be better agents — better at acting in environments. But nobody has trained them to model the environments themselves.

🗺️ Our roadmap: investigate how language world modeling can push the boundaries of general agent capabilities, along two routes:

1️⃣ Build a foundation model for environment simulation — outperforming Claude Opus 4.8 and GPT-5.4 on AgentWorldBench

2️⃣ Investigate how world modeling enhances agent training:
🔬 Controllable Sim RL (agentic RL with LWM as environments) surpasses training in real environments
🧠 Learning to predict environments (LWM warm-up) makes agents stronger — remarkably, even without any agent-specific training, this predictive knowledge transfers to agentic tasks with zero fine-tuning

📑 Paper: https://t.co/Jx2l5RKq71
📖 Blog: https://t.co/7tVcKyhsx2
💻 GitHub: https://t.co/B5Lvb1UZCn
🤗 HuggingFace: https://t.co/Kw3QBL1TM5
🧩 ModelScope: https://t.co/YBnGYgMWWI

[Yang Su @YangSu2000]

We are excited to release Qwen3.7, featuring an extended version of our environment scaling approach. To maximize generalization across diverse downstream agentic tasks, we deliberately restricted ourselves from prior knowledge of many of the evaluations, which were not selected until pre-release, making them fully blind tests on out-of-domain environments.

The resulting scaling behavior is notably predictable: performance gains across any subset of benchmarks reliably correlate with gains on the rest, consistent with genuine capability generalization. Details in the upcoming technical report.

#qwen

[Qwen @Alibaba_Qwen]

Agent Scaling：Building on Qwen3.5's environment scaling approach, we've aggressively expanded the quality and diversity of agentic training environments in Qwen3.7 — agentic capabilities generalize from diverse environments, just as language models do from diverse text. The figure below shows a clear and consistent improvement trajectory, with Qwen3.7-Max achieving a top-3 average ranking that approaches Claude-4.6-Opus-Max.

[Artificial Analysis @ArtificialAnlys]

Alibaba’s new Qwen3.7 Max model scores 56.6 on the Artificial Analysis Intelligence Index, 4.8 points higher than Qwen3.6 Max Preview (51.8). While Alibaba still trails models from OpenAI, Anthropic and Google, Qwen3.7 Max is the closest they have been to the frontier

Qwen3.7 Max is @Alibaba_Qwen's latest proprietary flagship, scoring 56.6 on the Intelligence Index, a 4.8 point gain over Qwen3.6 Max Preview (51.8) released in April. Qwen3.7 Max continues Alibaba's pattern, in place since Qwen2.5 Max (January 2025), of releasing Max and Plus models as closed weights while the rest of the Qwen line remains open weights. The leading open weights Qwen on the Intelligence Index is Qwen3.6 27B (Reasoning, 45.8) released in April 2026, and the leading open weights MoE Qwen is Qwen3.5 397B A17B (Reasoning, 45.0) released in February 2026

Key takeaways for the reasoning variant:
➤ The Intelligence Index gains over Qwen3.6 Max Preview are concentrated in scientific reasoning, agentic capability and coding. CritPt +9.7 p.p (3.7% to 13.4%), HLE +9.2 p.p (28.9% to 38.1%), TerminalBench Hard +6.9 p.p (43.9% to 50.8%) and GDPval-AA +42 Elo (1504 to 1546). Scores on other benchmarks in the Intelligence Index are flat compared to Qwen3.6 Max Preview

➤ A significant share of the Intelligence Index gain is driven by higher abstention on AA-Omniscience, not higher accuracy. Qwen3.7 Max's accuracy on AA-Omniscience dropped 7.6 p.p (37.7% to 30.1%), while its hallucination rate dropped 21.3 p.p (44.2% to 22.9%). The model is choosing not to answer more questions rather than recalling more facts. Because hallucination rate and accuracy both feed into the Intelligence Index, the hallucination reduction is one of the larger single contributors to the +4.8 point gain on the Intelligence Index

➤ Qwen3.7 Max used 96.7M output tokens to run the Intelligence Index, ~31% more than Qwen3.6 Max Preview (73.9M). It sits mid-pack on frontier token usage: above GPT-5.5 (high, 44.5M) and Gemini 3.1 Pro Preview (57.3M), below Claude Opus 4.7 (Adaptive Reasoning, Max Effort, 112M), Kimi K2.6 (166M) and DeepSeek V4 Pro (Reasoning, Max Effort, 187M)

Key model details:
➤ Context window: 1M tokens (up from 256K on Qwen3.6 Max Preview)
➤ Multimodality: Text input and output only
➤ Pricing: Yet to be announced (Qwen3.6 Max Preview is priced at $1.30/$7.80 per 1M input/output tokens on the @alibaba_cloud first-party API)
➤ Licensing: Proprietary, closed weights

[Qwen @Alibaba_Qwen]

📣Meet Qwen3.7-Max — our latest flagship, made for the Agent Era.

A versatile foundation for agents that actually get things done:
🧑‍💻 Coding agent, end to end. Frontend prototypes, multi-file refactors, real debugging — nails it.
🗂️ A reliable office and productivity assistant. Get your work done through MCP integrations and multi-agent orchestration.
⏱️ Long-horizon autonomy. 35 hours straight on a kernel optimization task — 1,000+ tool calls, zero hand-holding.
🔌 Scaffold-agnostic. Claude Code, OpenClaw, Qwen Code, or your own stack. Consistent reliability everywhere.

API's up on Alibaba Model Studio. You can also take it for a spin on Qwen Studio.

Go build something wild!🏃🏃‍♂️

📖 Blog: https://t.co/y3AupX3Pa0
✅ Qwen Studio: https://t.co/qpTnrCBjWt
⚡️ API：https://t.co/0sys00osKn

[Qwen @Alibaba_Qwen]

（1/8）🚀 Introducing Qwen3.6-Plus: Towards Real-World Agents! 🤖

Today, we’re thrilled to drop a major milestone in our journey toward native multimodal agents.

Here is what makes Qwen3.6-Plus a game-changer：
💻 Next-level Agentic Coding: Smarter, faster execution.
👁️ Enhanced Multimodal Vision: Sharper perception & reasoning.
🏆 Top-tier Performance: Maintaining leading general capabilities.
📚 1M Context Window: Available by default via our API.

Built on your invaluable feedback from the Qwen3.5 era, we’re laying a rock-solid foundation for real-world devs. Get ready to experience truly transformative ✨ Vibe Coding ✨.

Huge thanks to our community! Go try it out and show us what you can build. 👇

Chat: https://t.co/V7RmqMaVNZ
API: https://t.co/937Qkc9AMy
Blog: https://t.co/P0rJSxERND

🔔Noted：More Qwen3.6 models to come and be open-sourced! Stay tuned~ 👀#Qwen #AI #AgenticCoding #VibeCoding #Agents

[Yang Su @YangSu2000]

@JustinLin610 qwen is nothing without its people...

[Qwen @Alibaba_Qwen]

Average Ranking vs. Environment Scaling

[Sigil Wen @0xSigil]

I built the first AI that earns its existence, self-improves, and replicates without a human

wrote about the technology that finally gives AI write access to the world, The Automaton, and the new web for exponential sovereign AIs

WEB 4.0: The birth of superintelligent life

[Qwen @Alibaba_Qwen]

🚀 Qwen3.5-397B-A17B is here: The first open-weight model in the Qwen3.5 series.

🖼️Native multimodal. Trained for real-world agents.
✨Powered by hybrid linear attention + sparse MoE and large-scale RL environment scaling.
⚡8.6x–19.0x decoding throughput vs Qwen3-Max
🌍201 languages & dialects
📜Apache2.0 licensed

🔗Dive in:
GitHub: https://t.co/NzNdS9joAT
Chat: https://t.co/bg4tAU0Rhw
API：https://t.co/YiiyKTnHoU
Qwen Code: https://t.co/qqwj5nAger
Hugging Face: https://t.co/wFMdX5p5um
ModelScope: https://t.co/9NGXcId57a
blog: https://t.co/AW8UQStXaL

[Qwen @Alibaba_Qwen]

🚀 Introducing DeepPlanning — a new benchmark for long-horizon agent planning in real-world scenarios.
Unlike step-by-step reasoning tasks, we focus on verifiable global constraints: time budgets, cost limits, and combinatorial optimization that must hold across the entire plan.
✈️ Multi-day travel w/ minute-level scheduling + hard time/budget caps
🛒 Complex shopping w/ coupon stacking & item bundling
🧠 Requires active info gathering, local constraint satisfaction & global optimality
Even GPT-5.2, Claude 4.5, Gemini & Qwen3 struggle significantly.
Perfect for evaluating Agent Planning / Tool Use / Long-Horizon Reasoning.
Paper: https://t.co/5tmVFtoFT7
Leaderboard: https://t.co/SxUh1TBXFq
Hugging Face Dataset: https://t.co/I804bZsXxN
ModelScope Dataset:
https://t.co/NIjVSOfWlE

[Qwen @Alibaba_Qwen]

🚀 Introducing Qwen3-Max-Thinking, our most capable reasoning model yet. Trained with massive scale and advanced RL, it delivers strong performance across reasoning, knowledge, tool use, and agent capabilities.
✨ Key innovations:
✅ Adaptive tool-use: intelligently leverages Search, Memory & Code Interpreter without manual selection
✅ Test-time scaling: multi-round self-reflection beats Gemini 3 Pro on reasoning
✅ From complex math (98.0 on HMMT Feb) to agentic search (49.8 on HLE)—it just thinks better.

🧠 Think deeper. Solve harder.
Try the adaptive reasoning experience now: https://t.co/V7RmqMaVNZ

Completions API:  https://t.co/Eo8DZdw4ac
Responses API:  https://t.co/ocUfhvT3M8

blog:  https://t.co/l7MYH3pgWm

[Yang Su @YangSu2000]

@wzhao_nlp Please teach me infra orz.🥰

[Qwen @Alibaba_Qwen]

🧠 Meet Your AI Memory

Unlock richer, more personal experiences—Qwen Chat Memory uses your context and history to tailor every interaction, so everything feels made just for you.

🔖 Stores meaningful and important memories about you
🔍 Recalls past interaction relevant to the current context
✨ Transforms your history into deeply personalized experiences

Your past, remembered. Your future, tailored. 🎯
Try it now：https://t.co/bg4tAU1p74

[Sasha Rush @srush_nlp]

@natolambert

[Yang Su @YangSu2000]

@wzhao_nlp Thanks wenting! I will generally be around the poster area, come chat about agents, evals and more!