Pinned Tweet
Introducing Atria Dawn Preview: From Research Questions to Verifiable Results. Atria Dawn Preview is an agentic foundation model built for long-horizon tasks, helping researchers and engineers turn open-ended questions into executable, verifiable, and reproducible outcomes. Explore Atria Dawn Preview: 🌐 Website: atria-asi.ai/ 💻 GitHub: github.com/atria-asi/Atria-D… 🤗 Hugging Face: huggingface.co/internlm/Atri… 🤖 ModelScope: modelscope.cn/models/Shangha… 🚀 Try Atria: EN:api.atria-asi.ai/ ZH:discovery.intern-ai.org.cn/t…
346
398
2,468
4,434,559
Atria ASI retweeted
真实用户评价是最好的benchmark 很高兴我们的Atria-Dawn-Preview在一周内获得大量用户,并且收到了很多鼓励和好评,这样让我们更有动力做出更好的模型。 #atria #llm #ai #agent #bench
作为核心贡献者之一参与了这个项目,非常棒的团队。欢迎大家试用体验,免费的额度非常充足😘😘😘
5
2
18
2,105
Atria ASI retweeted
Stay tuned for Atria—more RSI explorations and exciting features are coming soon 🥳!
😃“From research questions to verifiable results” is the promise. 😉The proof? It ships. 🚀Meet Atria Dawn Preview @AtriaASI — an agentic foundation model for long-horizon tasks and controlled self-evolution, built on the Intern large model. 🌦️ 1 min → global weather forecast 🖥️ 20 min → OS from scratch 🧠 AI building AI, with verification in the loop Not uncontrolled RSI. Verifiable. Reproducible. Controllable. Open preview ↓ 🌐 atria-asi.ai 💻 github.com/atria-asi/Atria-D… 🤗 huggingface.co/internlm/Atri… 🤖 modelscope.cn/models/Shangha… 🐦 nitter.net/AtriaASI #AtriaDawn #AgenticAI #RSI #OpenSource
1
18
1,473
Atria ASI retweeted
😃“From research questions to verifiable results” is the promise. 😉The proof? It ships. 🚀Meet Atria Dawn Preview @AtriaASI — an agentic foundation model for long-horizon tasks and controlled self-evolution, built on the Intern large model. 🌦️ 1 min → global weather forecast 🖥️ 20 min → OS from scratch 🧠 AI building AI, with verification in the loop Not uncontrolled RSI. Verifiable. Reproducible. Controllable. Open preview ↓ 🌐 atria-asi.ai 💻 github.com/atria-asi/Atria-D… 🤗 huggingface.co/internlm/Atri… 🤖 modelscope.cn/models/Shangha… 🐦 nitter.net/AtriaASI #AtriaDawn #AgenticAI #RSI #OpenSource
8
5
78
7,219
Introducing Atria Dawn Preview: From Research Questions to Verifiable Results. Atria Dawn Preview is an agentic foundation model built for long-horizon tasks, helping researchers and engineers turn open-ended questions into executable, verifiable, and reproducible outcomes. Explore Atria Dawn Preview: 🌐 Website: atria-asi.ai/ 💻 GitHub: github.com/atria-asi/Atria-D… 🤗 Hugging Face: huggingface.co/internlm/Atri… 🤖 ModelScope: modelscope.cn/models/Shangha… 🚀 Try Atria: EN:api.atria-asi.ai/ ZH:discovery.intern-ai.org.cn/t…
346
398
2,468
4,434,559
We’re excited to highlight SETA, an open-source RL environment for training and evaluating AI agents from the @CamelAIOrg . A valuable resource for researchers and developers exploring agentic reinforcement learning and complex task environments. Check it out and support the CAMEL-AI community! 🚀 🔗 github.com/camel-ai/seta
12
6
59
3,851
Atria ASI retweeted
I'm also excited to share our team's study on human–AI collaboration. Throughout the training process, we (almost) achieved recursive self-improvement (RSI)— and I believe fully automated RSI is not far away🥳 .
From solving tasks to partnering on entire projects. We introduce Atria Dawn: The Dawn of Agentic Superintelligence — our study of what happens when agents move beyond answering questions to exploring, building, testing, and producing verifiable outcomes. 🔹 Verifiable Experience Pipeline 🔹 16 real-world benchmarks 🔹 #1 on 5 benchmarks 🔹 769 real task records from 56 participants 🔹 A case study of human–AI collaboration The goal isn’t just more capable agents. It’s agents that can contribute to real research and engineering workflows under human oversight. 📄 Paper: huggingface.co/papers/2609.1…
1
4
22
2,030
Meet Atria Dawn Preview, a new AI model from the Atria team, a collaboration between Shanghai AI Laboratory and multiple universities and research institutions. Built for scientific productivity, Atria Dawn Preview is designed to tackle complex research tasks continuously, turning long-horizon work into progressively verifiable outcomes. Its focus goes beyond solving individual tasks: Atria aims to strengthen end-to-end delivery in real-world workflows, from scientific automation to everyday office work. Website: atria-asi.ai/
2
6
52
3,141
We’re grateful to OpenBMB for supporting Atria Dawn Preview with UltraData-SFT-Agent-2609. The dataset’s high-quality agent trajectories have been valuable in developing Atria’s capabilities on agentic tasks. 🔗 huggingface.co/datasets/open…
5
11
82
6,250
From solving tasks to partnering on entire projects. We introduce Atria Dawn: The Dawn of Agentic Superintelligence — our study of what happens when agents move beyond answering questions to exploring, building, testing, and producing verifiable outcomes. 🔹 Verifiable Experience Pipeline 🔹 16 real-world benchmarks 🔹 #1 on 5 benchmarks 🔹 769 real task records from 56 participants 🔹 A case study of human–AI collaboration The goal isn’t just more capable agents. It’s agents that can contribute to real research and engineering workflows under human oversight. 📄 Paper: huggingface.co/papers/2609.1…
73
106
618
150,062
Cybersecurity Cybersecurity tasks put long-horizon agent capabilities to the test. In an authorized, isolated environment, Atria Dawn Preview combines environment understanding, vulnerability analysis, tool use, and result verification across the entire task. From analyzing an application and identifying its attack surface to validating vulnerabilities, executing exploits, and applying fixes, Atria carries the task through multiple stages with continuous verification. 🎥 See Atria Dawn Preview in action.
34
77
449
108,826
Delivery Atria Dawn Preview turns complex ideas and information into clear, compelling presentations—from understanding content and researching sources to structuring ideas and designing slides. Whether presenting a research paper or exploring an open-ended topic, Atria organizes key insights into coherent narratives and transforms them into polished, easy-to-understand slides. 🎥 See Atria Dawn Preview in action.
56
96
525
115,742
Creation Atria Dawn Preview can transform complex knowledge—people, spaces, events, and relationships—into intuitive, interactive digital experiences. From research and algorithms to cultural knowledge, Atria turns abstract information into spaces users can enter, explore, and understand. In the Dream of the Red Chamber demo, Atria reconstructs architecture, and spatial relationships into an explorable virtual world. 🎥 See Atria Dawn Preview in action.
17
47
266
39,656
Discovery For open-ended research questions, Atria Dawn Preview breaks down research goals, searches and evaluates sources, compares perspectives, and traces key evidence across sources. It turns scattered information into structured, citable, and verifiable research findings—helping researchers move beyond finding information toward building evidence and forming research judgments. 🎥 See Atria Dawn Preview in action.
21
64
473
80,074
From research and planning to coding, experimentation, and delivery, Atria connects the end-to-end workflow—accelerating scientific productivity and helping complex tasks move from questions to outcomes. Here’s a collection of real-world demos showcasing what Atria can do across research, creation, delivery, and cybersecurity.
23
49
330
46,035
Atria ASI retweeted
Introducing Atria Dawn Preview: From Research Questions to Verifiable Results. Atria Dawn Preview is an agentic foundation model built for long-horizon tasks, helping researchers and engineers turn open-ended questions into executable, verifiable, and reproducible outcomes. Explore Atria Dawn Preview: 🌐 Website: atria-asi.ai/ 💻 GitHub: github.com/atria-asi/Atria-D… 🤗 Hugging Face: huggingface.co/internlm/Atri… 🤖 ModelScope: modelscope.cn/models/Shangha… 🚀 Try Atria: EN:api.atria-asi.ai/ ZH:discovery.intern-ai.org.cn/t…
346
398
2,468
4,434,559
Atria ASI retweeted
Atria Dawn Preview @AtriaASI is now live — a new agentic model built for long-horizon tasks. From exploring a problem and designing solutions to writing code and validating experiments, Atria connects the research loop and keeps complex tasks moving toward executable, verifiable, reproducible results. Explore Atria Dawn Preview: 💻 GitHub: github.com/atria-asi/Atria-D… 🤗 Hugging Face: huggingface.co/internlm/Atri… 🌐 atria-asi.ai/ 🚀 Try Atria: api.atria-asi.ai/
36
52
620
81,201
Atria ASI retweeted
Introducing Atria Dawn Preview🫡: Atria is a 700B agentic foundation model for long-horizon task and real-world productivity 🙌 🌐 Homepage: atria-asi.ai 💻 GitHub: github.com/atria-asi/Atria-D… 🤗 Hugging Face: huggingface.co/internlm/Atri… 🚀Try it: api.atria-asi.ai
4
14
243
21,963
Atria ASI retweeted
Introducing Atria Dawn Preview🫡: Atria is a 700B agentic foundation model for long-horizon task and real-world productivity 🙌 🌐 Website: atria-asi.ai 💻 GitHub: github.com/atria-asi/Atria-D… 🤗 Hugging Face: huggingface.co/internlm/Atri… 🚀Try it: api.atria-asi.ai
Introducing Atria Dawn Preview: From Research Questions to Verifiable Results. Atria Dawn Preview is an agentic foundation model built for long-horizon tasks, helping researchers and engineers turn open-ended questions into executable, verifiable, and reproducible outcomes. Explore Atria Dawn Preview: 🌐 Website: atria-asi.ai/ 💻 GitHub: github.com/atria-asi/Atria-D… 🤗 Hugging Face: huggingface.co/internlm/Atri… 🤖 ModelScope: modelscope.cn/models/Shangha… 🚀 Try Atria: EN:api.atria-asi.ai/ ZH:discovery.intern-ai.org.cn/t…
1
4
48
6,634
Building a global weather forecasting system is a litmus test for AI coding ability. We did it — in a restricted environment with no web search: 🧠 Designed a ViT-backbone neural network with 400M+ parameters, trained over 45,000 steps to model 69 weather variables evolving over time ⚡ Predicts a full week of global weather in under 1 minute 📊 Surpasses NVIDIA's classic FourCastNet on several metrics — with less training data A research agent turning a research question into a runnable, verifiable experiment. And this is just the beginning. Coming soon. 🚀
15
22
97
43,297