Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction

TL;DR

This paper introduces Nex-N1, a large-scale agentic model trained in a scalable, diverse, and high-fidelity environment ecosystem, advancing autonomous decision-making in language models.

Contribution

The paper presents a comprehensive infrastructure for constructing complex, diverse, and realistic interactive environments to train large agentic models like Nex-N1.

Findings

Nex-N1 outperforms SOTA open-source models on benchmarks.

Nex-N1 achieves competitive results with proprietary models.

The ecosystem enables scalable and diverse environment creation.

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.