Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
- URL: http://arxiv.org/abs/2512.04987v1
- Date: Thu, 04 Dec 2025 16:57:02 GMT
- Title: Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
- Authors: Nex-AGI Team, :, Yuxuan Cai, Lu Chen, Qiaoling Chen, Yuyang Ding, Liwen Fan, Wenjie Fu, Yufei Gao, Honglin Guo, Pinxue Guo, Zhenhua Han, Zhengfu He, Hanglei Hu, Kai Hu, Shengjia Hua, Tianyu Huai, Baodai Huang, Li Ji, Zhen Jiang, Zhikai Lei, Bufan Li, Jiahang Lin, Lizhi Lin, Jinxiu Liu, Shichun Liu, Ziming Liu, Yuchen Ni, Pengfang Qian, Yujiong Shen, Qingyun Shi, Wentao Shu, Peng Sun, Yiran Suo, Tian Tang, Boyu Tian, Guoteng Wang, Junzhe Wang, Peixin Wang, Zhiheng Xi, Hang Yan, Jie Yang, Zhixiong Yang, Tianchu Yao, Guangze Ye, Qianxi Yu, Shuo Zhang, Xinyue Zhang, Yiqi Zhang, Jiarong Zhao, Miao Zheng, Rui Zheng, Enyu Zhou, Jiazheng Zhou, Maosen Zhou, Yuhao Zhou, Tao Gui, Yining Zheng, Xinchi Chen, Jie Zhou, Siyuan Feng, Qin Chen, Liang He, Qi Zhang, Xuanjing Huang, Xipeng Qiu,
- Abstract summary: We introduce a method designed to systematically scale the diversity and complexity of interactive environments.<n>Our method realizes this scaling by addressing three dimensions.<n>We train Nex-N1 upon the diverse and complex interactive environments established by our infrastructure.
- Score: 117.6380005194061
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms -- from static imitation to incentive-driven decision making. However, this transition is significantly impeded by the lack of scalable infrastructure capable of constructing high-quality interaction signals for effective policy learning. To address this, we introduce a comprehensive method designed to systematically scale the diversity and complexity of interactive environments. Our method realizes this scaling by addressing three orthogonal dimensions: (1) Complexity: NexAU, a flexible agent framework that supports building complex agent hierarchies via simple configurations; (2) Diversity: NexA4A automatically generates diverse agent hierarchies from natural language to cover infinite domains; and (3) Fidelity: NexGAP bridges the simulation-reality gap by integrating dynamic real-world environment for grounded trajectories synthesis. We train Nex-N1 upon the diverse and complex interactive environments established by our infrastructure. Empirical results on benchmarks such as SWE-bench and tau2 demonstrate that Nex-N1 consistently outperforms SOTA open-source models and achieves competitive performance against frontier proprietary models on complex agentic tasks. We open-source the Nex ecosystem and model weights to facilitate further research.
Related papers
- ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas [13.919124676472022]
ASTRA is an end-to-end framework for training tool-augmented language model agents.<n>ASTRA integrates scalable data synthesis and verifiable reinforcement learning.<n> Experiments on multiple agentic tool-use benchmarks demonstrate that ASTRA-trained models achieve state-of-the-art performance.
arXiv Detail & Related papers (2026-01-29T11:22:23Z) - Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models [78.73992315826035]
We introduce Youtu-LLM, a lightweight language model that harmonizes high computational efficiency with native agentic intelligence.<n>Youtu-LLM is pre-trained from scratch to systematically cultivate reasoning and planning capabilities.
arXiv Detail & Related papers (2025-12-31T04:25:11Z) - NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
arXiv Detail & Related papers (2025-10-15T16:25:18Z) - Flexible Swarm Learning May Outpace Foundation Models in Essential Tasks [0.0]
Foundation models have rapidly advanced AI, raising the question of whether their decisions will surpass human strategies in real-world domains.<n>Common challenge is adapting complex systems to dynamic environments.<n>We argue that monolithic foundation models face conceptual limits in overcoming it.<n>We propose a decentralized architecture of interacting small agent networks (SANs)
arXiv Detail & Related papers (2025-10-07T18:10:31Z) - Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents [0.0]
We propose an effective world model for decision-making that models the world's physics and its task semantics.<n>A systematic review of 2024 research in low-resource multi-agent soccer reveals a clear trend towards integrating symbolic and hierarchical methods.<n>We formalize this trend into a framework for Hierarchical Task Environments (HTEs), which are essential for bridging the gap between simple, reactive behaviors and sophisticated, strategic team play.
arXiv Detail & Related papers (2025-09-05T01:03:51Z) - Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate [1.0152838128195467]
The prevailing paradigm for scaling large language models (LLMs) involves monolithic, end-to-end training.<n>This paper explores an alternative, constructive scaling paradigm, enabled by the principle of emergent semantics in Transformers.<n>We operationalize this with a layer-wise constructive methodology that combines strict layer freezing in early stages with efficient, holistic fine-tuning of the entire model stack.
arXiv Detail & Related papers (2025-07-08T20:01:15Z) - High-Fidelity Scientific Simulation Surrogates via Adaptive Implicit Neural Representations [51.90920900332569]
Implicit neural representations (INRs) offer a compact and continuous framework for modeling spatially structured data.<n>Recent approaches address this by introducing additional features along rigid geometric structures.<n>We propose a simple yet effective alternative: Feature-Adaptive INR (FA-INR)
arXiv Detail & Related papers (2025-06-07T16:45:17Z) - Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems [69.95482609893236]
Large Language Model-based Multi-Agent Systems (MASs) have emerged as a powerful paradigm for tackling complex tasks through collaborative intelligence.<n>We call for a paradigm shift toward emphtopology-aware MASs that explicitly model and dynamically optimize the structure of inter-agent interactions.
arXiv Detail & Related papers (2025-05-28T15:20:09Z) - Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models [106.35361897941898]
We propose a novel world model for Multi-Agent RL (MARL) that learns decentralized local dynamics for scalability.<n>We also introduce a Perceiver Transformer as an effective solution to enable centralized representation aggregation.<n>Results on Starcraft Multi-Agent Challenge (SMAC) show that it outperforms strong model-free approaches and existing model-based methods in both sample efficiency and overall performance.
arXiv Detail & Related papers (2024-06-22T12:40:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.