In this report, we present Qwen2.5-Omni, an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner. To enable the streaming of multimodal information inputs, both audio and visual encoders utilize a block-wise processing approach. To synchronize the timestamps of video inputs with audio, we organize the audio and video sequentially in an interleaved manner and propose a novel position embedding approach, named TMRoPE(Time-aligned Multimodal RoPE). To concurrently generate text and speech while avoiding interference between the two modalities, we propose \textbf{Thinker-Talker} architecture. In this framework, Thinker functions as a large language model tasked with text generation, while Talker is a dual-track autoregressive model that directly utilizes the hidden representations from the Thinker to produce audio tokens as output. Both the Thinker and Talker models are designed to be trained and inferred in an end-to-end manner. For decoding audio tokens in a streaming manner, we introduce a sliding-window DiT that restricts the receptive field, aiming to reduce the initial package delay. Qwen2.5-Omni is comparable with the similarly sized Qwen2.5-VL and outperforms Qwen2-Audio. Furthermore, Qwen2.5-Omni achieves state-of-the-art performance on multimodal benchmarks like Omni-Bench. Notably, Qwen2.5-Omni's performance in end-to-end speech instruction following is comparable to its capabilities with text inputs, as evidenced by benchmarks such as MMLU and GSM8K. As for speech generation, Qwen2.5-Omni's streaming Talker outperforms most existing streaming and non-streaming alternatives in robustness and naturalness.

--Integrating the structural inductive biases of Graph Neural Networks (GNNs) with the global contextual modeling capabilities of Transformers represents a pivotal challenge in graph representation learning. While GNNs excel at capturing localized topological patterns through message-passing mechanisms, their inherent limitations in modeling long-range dependencies and parallelizability hinder their deployment in large-scale scenarios. Conversely, Transformers leverage self-attention mechanisms to achieve global receptive fields but struggle to inherit the intrinsic graph structural priors of GNNs. This paper proposes a novel knowledge distillation framework that systematically transfers multiscale structural knowledge from GNN teacher models to Transformer student models, offering a new perspective on addressing the critical challenges in cross-architectural distillation. This work establishes a new paradigm for inheriting graph structural biases in Transformer architectures, with broad application prospects.

We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.

With the rapid development of large models in the field of artificial intelligence, how to enhance their application capabilities in handling complex problems in the field of scientific research remains a challenging problem to be solved. This study proposes an improved Monte Carlo Tree Search (MCTS) method based on prompt words. In the simulation search stage, it introduces dynamic adjustment of exploration parameters and adaptive selection strategies, which can better balance exploration and exploitation, thereby reducing the hallucination phenomenon. This paper takes the four subsets of the SciEval dataset as the test objects, and compares the Glm-4-flash+Improved MCTS method with the methods of several existing models. The results show that the Improved MCTS method performs better, providing new ideas and methods for the application of large models in the field of scientific research.

This study explores the integration of Agent AI with LangGraph to enhance real-time data analysis systems in big data environments. The proposed framework overcomes limitations of static workflows, inefficient stateful computations, and lack of human intervention by leveraging LangGraph's graph-based workflow construction and dynamic decision-making capabilities. LangGraph allows large language models (LLMs) to dynamically determine control flows, invoke tools, and assess the necessity of further actions, improving flexibility and efficiency. The system architecture incorporates Apache Spark Streaming, Kafka, and LangGraph to create a high-performance sentiment analysis system. LangGraph's capabilities include precise state management, dynamic workflow construction, and robust memory checkpointing, enabling seamless multi-turn interactions and context retention. Human-in-the-loop mechanisms are integrated to refine sentiment analysis, particularly in ambiguous or high-stakes scenarios, ensuring greater reliability and contextual relevance. Key features such as real-time state streaming, debugging via LangGraph Studio, and efficient handling of large-scale data streams make this framework ideal for adaptive decision-making. Experimental results confirm the system's ability to classify inquiries, detect sentiment trends, and escalate complex issues for manual review, demonstrating a synergistic blend of LLM capabilities and human oversight. This work presents a scalable, adaptable, and reliable solution for real-time sentiment analysis and decision-making, advancing the use of Agent AI and LangGraph in big data applications.

This paper presents a Spark-based modular LangGraph framework, designed to enhance machine learning workflows through scalability, visualization, and intelligent process optimization. At its core, the framework introduces Agent AI, a pivotal innovation that leverages Spark's distributed computing capabilities and integrates with LangGraph for workflow orchestration. Agent AI facilitates the automation of data preprocessing, feature engineering, and model evaluation while dynamically interacting with data through Spark SQL and DataFrame agents. Through LangGraph's graph-structured workflows, the agents execute complex tasks, adapt to new inputs, and provide real-time feedback, ensuring seamless decision-making and execution in distributed environments. This system simplifies machine learning processes by allowing users to visually design workflows, which are then converted into Spark-compatible code for high-performance execution. The framework also incorporates large language models through the LangChain ecosystem, enhancing interaction with unstructured data and enabling advanced data analysis. Experimental evaluations demonstrate significant improvements in process efficiency and scalability, as well as accurate data-driven decision-making in diverse application scenarios. This paper emphasizes the integration of Spark with intelligent agents and graph-based workflows to redefine the development and execution of machine learning tasks in big data environments, paving the way for scalable and user-friendly AI solutions.

This paper explores the transformative role of Agent AI and LangGraph in advancing the automation and effectiveness of machine translation (MT). Agents are modular components designed to perform specific tasks, such as translating between particular languages, with specializations like TranslateEnAgent, TranslateFrenchAgent, and TranslateJpAgent for English, French, and Japanese translations, respectively. These agents leverage the powerful semantic capabilities of large language models (LLMs), such as GPT-4o, to ensure accurate, contextually relevant translations while maintaining modularity, scalability, and context retention. LangGraph, a graph-based framework built on LangChain, simplifies the creation and management of these agents and their workflows. It supports dynamic state management, enabling agents to maintain dialogue context and automates complex workflows by linking agents and facilitating their collaboration. With flexibility, open-source community support, and seamless integration with LLMs, LangGraph empowers agents to deliver high-quality translations. Together, Agent AI and LangGraph create a cohesive system where LangGraph orchestrates agent interactions, ensuring that user inputs are analyzed, routed, and processed efficiently. Experimental results demonstrate the potential of this system to enhance multilingual translation accuracy and scalability. By highlighting modular design and automated workflows, this paper sets the stage for further innovations in intelligent machine translation services.

With the rapid development of large model technology, the application of agent technology in various fields is becoming increasingly widespread, profoundly changing people's work and lifestyles. In complex and dynamic systems, multi-agents achieve complex tasks that are difficult for a single agent to complete through division of labor and collaboration among agents. This paper discusses the integrated application of LangGraph and CrewAI. LangGraph improves the efficiency of information transmission through graph architecture, while CrewAI enhances team collaboration capabilities and system performance through intelligent task allocation and resource management. The main research contents of this paper are: (1) designing the architecture of agents based on LangGraph for precise control; (2) enhancing the capabilities of agents based on CrewAI to complete a variety of tasks. This study aims to delve into the application of LangGraph and CrewAI in multi-agent systems, providing new perspectives for the future development of agent technology, and promoting technological progress and application innovation in the field of large model intelligent agents.

Abstract--Large Language Models (LLMs) still face challenges when dealing with complex reasoning tasks, often resulting in hallucinations, which limit the practical application of LLMs. To alleviate this issue, this paper proposes a new method that integrates different LLMs to expand the knowledge boundary, reduce dependence on a single model, and promote in-depth debate among agents. The main contributions include: 1) Introducing third-party LLMs to adjust the attention weights of agents through uncertainty estimation and confidence analysis, optimizing consensus formation in multi-agent systems; 2) Experiments on arithmetic datasets have validated the effectiveness of the method, surpassing traditional multi-agent baselines. This research provides a new perspective for large models to alleviate hallucination phenomena when dealing with complex tasks. In these systems, multiple agents articulate their arguments, while a neutral moderator oversees the debate process to facilitate the attainment of a final resolution Therefore, this paper raises a question: Can a third-party [2].By employing multiple instances of language models and model be introduced to complete tasks through the collaboration engaging in several rounds of proposal and debate regarding of multiple Large Language Models?

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing a parameter range from 0.5 to 72 billion, featuring dense models and a Mixture-of-Experts model. Qwen2 surpasses most prior open-weight models, including its predecessor Qwen1.5, and exhibits competitive performance relative to proprietary models across diverse benchmarks on language understanding, generation, multilingual proficiency, coding, mathematics, and reasoning. The flagship model, Qwen2-72B, showcases remarkable performance: 84.2 on MMLU, 37.9 on GPQA, 64.6 on HumanEval, 89.5 on GSM8K, and 82.4 on BBH as a base language model. The instruction-tuned variant, Qwen2-72B-Instruct, attains 9.1 on MT-Bench, 48.1 on Arena-Hard, and 35.7 on LiveCodeBench. Moreover, Qwen2 demonstrates robust multilingual capabilities, proficient in approximately 30 languages, spanning English, Chinese, Spanish, French, German, Arabic, Russian, Korean, Japanese, Thai, Vietnamese, and more, underscoring its versatility and global reach. To foster community innovation and accessibility, we have made the Qwen2 model weights openly available on Hugging Face and ModelScope, and the supplementary materials including example code on GitHub. These platforms also include resources for quantization, fine-tuning, and deployment, facilitating a wide range of applications and research endeavors.