Related papers: Qwen3-Coder-Next Technical Report

Code language models have emerged as useful tools for various programming tasks, yet they often struggle when it comes to complex ones. In this paper, we explore the potential of curriculum learning in enhancing the performance of these…

We present INTELLECT-3, a 106B-parameter Mixture-of-Experts model (12B active) trained with large-scale reinforcement learning on our end-to-end RL infrastructure stack. INTELLECT-3 achieves state of the art performance for its size across…

Agents based on large language models leverage tools to modify environments, revolutionizing how AI interacts with the physical world. Unlike traditional NLP tasks that rely solely on historical dialogue for responses, these agents must…

Practical guidance on training Large Language Models (LLMs) to leverage Code Interpreter across diverse tasks remains lacking. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning…

Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires…

Learning in environments with large state and action spaces, and sparse rewards, can hinder a Reinforcement Learning (RL) agent's learning through trial-and-error. For instance, following natural language instructions on the Web (such as…

We propose that small pretrained foundational generative language models with millions of parameters can be utilized as a general learning framework for sequence-based tasks. Our proposal overcomes the computational resource, skill set, and…

The development of artificial intelligence systems is transitioning from creating static, task-specific models to dynamic, agent-based systems capable of performing well in a wide range of applications. We propose an Interactive Agent…

Large language models deliver strong reasoning and tool-use skills, yet their computational demands make them impractical for edge or cost-sensitive deployments. We present \textbf{Xmodel-2.5}, a 1.3-billion-parameter small language model…

Recently, instruction-following audio-language models have received broad attention for audio interaction with humans. However, the absence of pre-trained audio models capable of handling diverse audio types and tasks has hindered progress…

Xmodel-2 is a 1.2-billion-parameter large language model designed specifically for reasoning tasks. Its architecture enables different model scales to share a unified set of hyperparameters, allowing for extensive experimentation on smaller…

In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline,…

We present Qwen3-Omni, a single multimodal model that, for the first time, maintains state-of-the-art performance across text, image, audio, and video without any degradation relative to single-modal counterparts. Qwen3-Omni matches the…

Large Language Models (LLMs) are becoming increasingly powerful and capable of handling complex tasks, e.g., building single agents and multi-agent systems. Compared to single agents, multi-agent systems have higher requirements for the…

Production agentic systems make many model calls per user request, and most of those calls are short, structured, and routine. This raises a practical routing question that existing evaluations do not directly answer: which parts of an…

Since the Transformer architecture emerged, language model development has grown, driven by their promising potential. Releasing these models into production requires properly understanding their behavior, particularly in sensitive domains…

Learning deeper models is usually a simple and effective approach to improve model performance, but deeper models have larger model parameters and are more difficult to train. To get a deeper model, simply stacking more layers of the model…

Large language models (LLMs) already excel at writing code in high-resource languages such as Python and JavaScript, yet stumble on low-resource languages that remain essential to science and engineering. Besides the obvious shortage of…

In this paper, we present a comprehensive study of language interference in encoder-only Transformer models across 83 languages. We construct an interference matrix by training and evaluating small BERT-like models on all possible language…

With the rapid development of mobile intelligent assistant technologies, multi-modal AI assistants have become essential interfaces for daily user interactions. However, current evaluation methods face challenges including high manual…