Nex (@NexEcosystem) - Twitter-Profil | Zamantika Mersobahis Locabet

Angehefteter Tweet

Nex@NexEcosystem·3d

📢 Nex-N2 is here! A family of agentic models that doesn't just think, it acts! Coding, search, tool use. All fused into a single agentic reasoning loop. - Adaptive Thinking, auto-scales reasoning depth per step. Saves ~20% tokens, zero performance loss. - Coherent Thinking, one thinking paradigm across search, coding, and tool use. No more fragile mode-switching. 🏆 Result: Tier-1 open-source performance on SWE-bench, Terminal-Bench, GDPval, and more, tracking GPT-5.5 and Opus 4.7. 🎉 Open-weight. Try it now. 🔗 nex-agi.com 📦 huggingface.co/nex-agi/Nex-N2… modelscope.cn/models/nex-agi… github.com/nex-agi/Nex-N2

English

7

8

26

1.4K

Nex@NexEcosystem·2d

Nex-N2-Pro now free for 2 weeks on @SiliconFlowAI! 30-50% fewer thinking tokens with zero performance trade-off. Give it a try ⚡

SiliconFlow@SiliconFlowAI

Post-training is having a moment — Nex-N2-Pro from neolab @NexEcosystem proves it. Built on Qwen3.5-397B-A17B, delivers GPT-5.5 and Claude Opus 4.7–level performance. 🎉 T+0 Support on SiliconFlow · Free for First 2 Weeks N2-Pro: 397B MoE / Reasoning Model / 262K context / VLM → Auto-adjusts reasoning depth, 30–50% fewer thinking tokens, no performance trade-off → SOTA performance on Terminal Bench 2.1, GDPVal, SWE-Verified → Excels at agentic coding, deep search, tool use → Plug-and-play with Claude Code, Cursor, OpenClaw, etc. Try it on SiliconFlow ⬇️

English

2

0

9

450

Nex@NexEcosystem·2d

@SiliconFlowAI Thanks @SiliconFlowAI for the T+0 support and free trial! Great way to let developers try Nex-N2-Pro hands-on 🙌

English

1

0

135

SiliconFlow@SiliconFlowAI·3d

Post-training is having a moment — Nex-N2-Pro from neolab @NexEcosystem proves it. Built on Qwen3.5-397B-A17B, delivers GPT-5.5 and Claude Opus 4.7–level performance. 🎉 T+0 Support on SiliconFlow · Free for First 2 Weeks N2-Pro: 397B MoE / Reasoning Model / 262K context / VLM → Auto-adjusts reasoning depth, 30–50% fewer thinking tokens, no performance trade-off → SOTA performance on Terminal Bench 2.1, GDPVal, SWE-Verified → Excels at agentic coding, deep search, tool use → Plug-and-play with Claude Code, Cursor, OpenClaw, etc. Try it on SiliconFlow ⬇️

English

8

3

24

2.3K

Nex@NexEcosystem·2d

Nex-N2-Pro now available on @novita_labs! Try it out if you're building coding agents or research workflows 🚀

Novita AI@novita_labs

🚀 Nex-N2-Pro from @NexEcosystem is now available on Novita AI. An open-source agentic reasoning model post-trained on Qwen3.5-397B-A17B MoE, built for coding agents, software engineering, and deep research workflows. Nex-N2-Pro brings: • Agentic Thinking for complex workflows Unifies reasoning, tool use, and environment execution for long-horizon tasks • Strong coding + terminal performance Scores 75.3 on Terminal-Bench 2.1 and 80.8 on SWE-Bench Verified • Designed for self-evolving harnesses Specifically optimized for Agentic Harness Engineering (AHE), with top-tier pass@1 performance reaching 69.0% in a SQL interpreter self-evolution task • Fast, developer-ready access Run Nex-N2-Pro through Novita’s API with simple integration Excited to bring Nex-N2-Pro to developers on Novita.

English

0

1

3

214

Novita AI@novita_labs·3d

🚀 Nex-N2-Pro from @NexEcosystem is now available on Novita AI. An open-source agentic reasoning model post-trained on Qwen3.5-397B-A17B MoE, built for coding agents, software engineering, and deep research workflows. Nex-N2-Pro brings: • Agentic Thinking for complex workflows Unifies reasoning, tool use, and environment execution for long-horizon tasks • Strong coding + terminal performance Scores 75.3 on Terminal-Bench 2.1 and 80.8 on SWE-Bench Verified • Designed for self-evolving harnesses Specifically optimized for Agentic Harness Engineering (AHE), with top-tier pass@1 performance reaching 69.0% in a SQL interpreter self-evolution task • Fast, developer-ready access Run Nex-N2-Pro through Novita’s API with simple integration Excited to bring Nex-N2-Pro to developers on Novita.

English

9

3

26

1.2K

Nex@NexEcosystem·2d

@novita_labs Thanks for bringing Nex-N2-Pro to Novita! Excited to see developers build with it. Let us know how it goes 🙌

English

0

1

82

Nex retweetet

Dawning Road@TheDawningRoad·22 Oca

Introduce NexRL: Extreme Usability We aim to develop an extremely user-friendly RL framework, with four main principles: 1. Extremely Lightweight 2. Extremely Community-Driven 3. Extremely Extensible 4. Long-Term Maintainability NexRL adopts an ultra-loosely-coupled architectural design, with core characteristics embodied in component modularization and training-inference service-orientation. Along with Nex ecosystem @NexEcosystem , NexRL has already boosted agent training, on-policy-distillation, and training API serving (see our previous blog dawning-road.github.io/blog/deep-dive…). Details at: dawning-road.github.io/blog/nexrl

English

0

6

485

Nex retweetet

Dawning Road@TheDawningRoad·6 Şub

Introduce Scalable Interactive Oversight. In vibe coding, users often fall into prolonged feedback–iteration loops. This reflects a scalable oversight problem: humans act as "weak supervisors", struggling to precisely articulate complex intent and to verify long-horizon outputs; meanwhile, models function as "strong executors", capable of efficient task execution but increasingly difficult to steer with reliable alignment signals. Scalable Interactive Oversight decomposes complex intent into a recursive tree of manageable decisions to amplify human supervision. It can be optimized via Reinforcement Learning using only online user feedback, offering a practical pathway for maintaining human control as AI scales. Details at: dawning-road.github.io/blog/scalable-…

English

2

4

6

334

Nex retweetet

Dawning Road@TheDawningRoad·20 Oca

We release ABC-bench with @Open_MOSS. It benchmarks the agents' ability to reliably deliver production-grade backend services. Findings: 1. Full-lifecycle tasks pose significant challenges for all models. 2. Models generally lack cross-language robustness. 3. Environment configuration is the primary source of performance bottlenecks. Details at: dawning-road.github.io/blog/abc-bench

English

1

5

6

264

Nex retweetet

Dawning Road@TheDawningRoad·8 Oca

Introducing Weaver: our Training-as-a-Service platform. Weaver is a training API designed for researchers and developers working with LLMs, inspired by Tinker @thinkymachines . As an ecosystem-oriented product, it seamlessly integrates with agent frameworks and reinforcement learning training frameworks, enabling flexible fine-tuning of agentic models. Weaver lets you focus on what matters – your data, algorithms and agents – while handling the complexity of distributed training infrastructure. Focus on the science. We’ll handle the rest. Details at: dawning-road.github.io/blog/deep-dive…

English

1

7

10

405

Nex@NexEcosystem·24 Ara

Speed matters. ⚡️ Thrilled to collaborate with @lmsysorg on SpecBundle! We’ve trained dedicated EAGLE-3 draft models for our Nex-N1 series. By combining SGLang with our draft models, you can now achieve massive inference speedups: 🚀 2.26x on Qwen3-32B-Nex-N1 🚀 1.68x on Qwen3-30B-A3B-Nex-N1 Unlock lower latency for your agents today. 👇 #NexN1 #SGLang #SpeculativeDecoding #OpenSource

LMSYS Org@lmsysorg

Speculative decoding has shown a lot of promise, though broader adoption has taken time due to the complexity of building production-ready tooling and high-quality draft models. We’re releasing SpecBundle, a collection of large-scale EAGLE-3 draft models trained with SpecForge v0.2. This release brings major system improvements, including refactored training pipelines, multi-backend support with SGLang and @huggingface , and better usability at scale. We also built a performance dashboard to make real end-to-end speedups visible across models and settings. See the dashboard and blog in the thread 👇

English

2

1

5

148

Nex@NexEcosystem·15 Ara

Mark your calendars! 📅 Join us for a deep dive into the Nex Ecosystem! Topic👉 Nex: The Next-Gen Agentic Model System & Open Source Ecosystem ⏰ Time: Dec 16th, 20:00 (UTC+8) / 12:00 (UTC) 📍 Host: ModelScope & Shanghai Foundation Model Innovation Center Scan the QR code in the image to reserve your spot! 👇 #ModelScope #OpenSource #AI #LiveStream

English

0

1

7

117

Nex@NexEcosystem·25 Kas

We’re open-sourcing Nex, the Next-Generation Agentic Models & Open-Source Ecosystem. The Nex-N1 model series (8B-671B) offers leading performance on tool-use and agent capabilities, excelling in coding, web search, and interactive WeChat mini program. Nex ecosystem includes synthesis pipelines, high-quality datasets, and frameworks for agent development, reinforcement learning, and MoE Inference. Fully open-sourced on GitHub, Hugging Face, and ModelScope. OpenRouter API and technical report coming soon.

English

4

18

340

Nex retweetet

Dawning Road@TheDawningRoad·11 Ara

FP8 series Part II: We introduce a ZeRO optimizer implementation scheme adapted for Hopper architecture and oriented toward Blockwise quantization. This optimizer has been thoroughly validated in our team's internal native FP8 SFT and RL tasks based on the DeepSeek architecture. Details at: dawning-road.github.io/blog/fp8-zero1

English

1

8

12

370

Nex retweetet

Dawning Road@TheDawningRoad·3 Ara

On-policy RL is stable but slow. Off-policy RL is efficient but unstable. Our new analysis reveals why off-policy breaks—optimization imbalance + entropy clipping effects. Meet BAPO: a balanced, adaptive clipping method that finally makes off-policy RL stable for long-horizon LLM training. Details at: dawning-road.github.io/blog/bapo

English

3

9

15

284

Nex@NexEcosystem·11 Ara

🔥 UPDATE: We are live on @openrouter! For developers who prefer a unified API gateway, you can now access #NexN1 directly on OpenRouter. ✨ Tier: Free (Currently) 🆔 Model ID: nex-agi/deepseek-v3.1-nex-n1:free Switch your endpoint and start building agents in seconds. 👇 openrouter.ai/nex-agi/deepse…

English

0

10

14

2K

Nex@NexEcosystem·25 Kas

Want to build with #Nex? 🛠️ Huge shoutout to @Codedigipt for this deep dive into the Nex ecosystem! 🚀 He just dropped a fantastic step-by-step tutorial. A perfect resource for developers looking to get started with Nex-N1.👇 youtube.com/watch?v=RZWPrr… #Coding #DevCommunity #AI #OpenSource #AgenticAI #LLMs

YouTube

English

1

4

204

Nex@NexEcosystem·5 Ara

Nex-N1 technical report is now out on arXiv! 🚀 Dive in: arxiv.org/abs/2512.04987 From architecture and data to training pipelines, evaluation, and inference — the report provides a full overview of the Nex: 🧩 Generative Environments: toward scalable, automated environment synthesis 📚 Nex-N1 Series (8B–671B): showing strong results across multiple agentic benchmarks 🛠️ Agentic Capabilities: steady improvements in coding, tool use, and interactive tasks 🔧 Open Source: including data, RL pipelines, and MoE inference implementations As always, the Nex ecosystem remains fully open-source on GitHub, Hugging Face, and ModelScope. Thanks for checking it out!

English

0

8

12

233

Nex retweetet

ModelScope@ModelScope2022·24 Kas

Meet Nex by NEX-AGI — a non-thinking model built for agents that crushes it in coding, tool use, and roleplay 🚀 ✅ SOTA among open models on Tau2-Bench, BFCL V4, GAIA2 ✅ Top-tier in frontend, vibe coding, and mini-program/backend dev (human eval confirmed) ✅ Plug-and-play with Claude Code, Cursor, etc. 👉 Expolore Nex: modelscope.cn/organization/n… 🔥 Free for now on SiliconFlow: siliconflow.com/models/deepsee…

English

4

27

111

8.3K

Nex retweetet

Tiezhen WANG@Xianbao_QIAN·22 Kas

Welcome Nex-N1, a new series of agentic foundational models, to @huggingface - available in different sizes from 8B, 30B, 32B to 671B - strong in tool-use, web-search and real-world agentic workflow - some SFT dataset has been open sourced Technical report come up soon!

English

18

72

457

82.1K

Nex retweetet

Dawning Road@TheDawningRoad·27 Kas

We rebuilt Grouped Per-Token Quantization at the kernel level — removing the real bottleneck in FP8/MoE training and pushing efficiency to the hardware limit: • 20× faster core ops • ~2.7 TB/s effective throughput Details at: dawning-road.github.io/blog/grouped-f…

English

0

9

19

302

Nex

Entdecken