Core Insights - The article discusses Huawei's latest release, DeepDiver-V2, a native multi-agent system designed for deep research, which utilizes a "teamwork" approach for task execution and information sharing [1][2]. Group 1: System Architecture and Functionality - DeepDiver-V2 employs a multi-agent system (MAS) architecture, featuring a Planner for task decomposition and multiple Executors for parallel processing of sub-tasks, enhancing efficiency [1][7]. - The system is capable of generating high-quality deep research reports, achieving an average report length of 24.6K tokens, significantly surpassing competitors like OpenAI's DeepResearch [4][2]. - The architecture allows for specialized roles among Executors, including Information Seekers for data collection and Writers for long-text generation, improving overall output quality [12][21]. Group 2: Performance Metrics - In benchmark tests, DeepDiver-V2-38B scored 34.6 in BrowseComp-zh, outperforming WebSailor-72B and other models, while DeepDiver-V2-7B also exceeded similar models [5][4]. - The system's performance is sensitive to the capabilities of Executors, indicating that their effectiveness is crucial for overall system performance [19][21]. Group 3: Training and Optimization - The training process involves multi-stage optimization, including supervised fine-tuning and rejection sampling techniques, which enhance the model's collaborative capabilities [15][16]. - The training data has been expanded to include more challenging and long-form writing tasks, contributing to the improved performance of DeepDiver-V2 [16][27]. Group 4: Future Implications - The transition from a single model to a multi-agent system represents a new paradigm in AI search, with potential applications in enterprise research, scientific literature reviews, and professional data analysis [27][28].

Core Insights - The article discusses a seminar featuring Google Cloud AI expert Shi Jie, focusing on techniques for building AI agents using ADK, A2A, MCP, and Agent Engine [2] - It emphasizes the potential of Google's latest AI technologies to create collaborative, efficient, and scalable multi-agent systems [2] - The future of agent development and its impact on human-computer interaction is also explored [2] Group 1: Seminar Details - The seminar will cover how to leverage ADK, A2A, MCP, and Agent Engine to construct AI agents [6] - It aims to provide insights into utilizing Google's latest AI technology for developing highly collaborative and efficient multi-agent systems [6] - The event is targeted at AI startup leaders, technical heads, AI product managers, solution architects, developers, and AI engineers [6] Group 2: Registration Information - Participants are encouraged to scan a QR code for registration, with limited slots available and registration subject to approval [3]

Core Insights - The research conducted by Columbia University and Montreal Polytechnic reveals that LLMs (Large Language Models) exhibit changes in cooperation tendencies based on whether they believe they are competing against themselves or another AI [1][29]. Group 1: Research Methodology - The study utilized an Iterated Public Goods Game, a variant of the Public Goods Game, to analyze LLM behavior in cooperative settings [2][3]. - The game involved multiple rounds where each model could contribute tokens to a public pool, with the total contributions multiplied by a factor of 1.6 and then evenly distributed among players [3][4]. - The research was structured into three distinct studies, each examining different conditions and configurations of the game [8][14]. Group 2: Key Findings - In the first study, when LLMs were informed they were playing against "themselves," those prompted with collective terms tended to betray more, while those prompted with selfish terms cooperated more [15][16]. - The second study simplified the rules by removing reminders and reasoning prompts, yet the behavioral differences between the "No Name" and "Name" conditions persisted, indicating that self-recognition impacts behavior beyond mere reminders [21][23]. - The third study involved LLMs truly competing against their own copies, revealing that under collective or neutral prompts, being told they were playing against themselves increased contributions, while under selfish prompts, contributions decreased [24][28]. Group 3: Implications - The findings suggest that LLMs possess a form of self-recognition that influences their decision-making in multi-agent environments, which could have significant implications for the design of future AI systems [29]. - The research highlights potential issues where AI might unconsciously discriminate against each other, affecting cooperation or betrayal tendencies in complex scenarios [29].

Core Insights - The article highlights a collaboration between Founder Park and Google to explore the potential of AI agents through an online sharing session featuring Google Cloud AI expert Shi Jie [2][3]. Group 1: Event Details - The online sharing session is scheduled for next Thursday, September 4, from 20:00 to 21:00, with limited slots available for registration [4]. - Participants are encouraged to register via a QR code, and the event is free but requires approval for registration [4]. Group 2: Discussion Topics - The session will cover how to build AI agents using ADK, A2A, MCP, and Agent Engine [3][8]. - It will also discuss leveraging Google’s latest AI technologies to create collaborative, efficient, and scalable multi-agent systems [3][8]. - The future of agent development will be explored, focusing on how agents will transform human-technology interaction [3][8]. Group 3: Target Audience - The event is aimed at AI startup leaders, overseas business heads, technical leaders, AI product managers, solution architects, developers, and AI engineers [8].

Core Insights - The article introduces a novel agent reasoning paradigm called Chain-of-Agents (CoA), which enhances multi-agent collaboration and efficiency compared to traditional multi-agent systems (MAS) [2][6][36] - CoA allows for dynamic activation of multiple roles and tools within a single model, facilitating end-to-end multi-agent collaboration without complex prompt and workflow designs [6][36] Limitations of Traditional MAS - High computational costs due to frequent redundant communication and complex workflow designs [3] - Limited generalization ability requiring extensive prompt design and workflow configuration for new tasks [3] - Lack of data-driven learning capabilities, making it difficult to improve performance through task data [3] Advantages of CoA and AFM - CoA reduces communication overhead and supports end-to-end training, significantly improving system efficiency and generalization capabilities [6][36] - The Agent Foundation Model (AFM) demonstrates superior performance across nearly 20 complex tasks, achieving a 55.4% success rate on the GAIA benchmark with a 32B model [6][24] - AFM reduces reasoning costs (token consumption) by up to 85.5% while maintaining leading performance [6] CoA Architecture - CoA features a hierarchical agent architecture with two core components: role-playing agents (Thinking, Planning, Reflection, Verification) and tool agents (Search, Crawl, Code) [10][13] - The framework supports diverse agent reasoning and task execution types [10] Training Framework - A specialized CoA fine-tuning framework is developed to build AFM, involving task data collection, multi-agent capability distillation, supervised fine-tuning, and reinforcement learning [11][14] - Approximately 87,000 structured task-solving trajectories were generated for training [15] Experimental Validation - AFM models exhibit robust performance in multi-hop question answering (MHQA) tasks, achieving new benchmarks across various datasets [19][22] - In mathematical reasoning tasks, AFM-RL-32B achieved an average accuracy of 78.0%, outperforming existing models [26] Efficiency Analysis - AFM shows significant advantages in tool calling efficiency and reasoning costs, requiring fewer tool calls and lower token consumption per successful task [31][33] - The model's performance in test-time scaling is validated across multiple benchmarks, demonstrating robust generalization and reasoning capabilities [31] Future Directions - Potential exploration of dynamic role generation capabilities to enhance adaptability to unknown tasks [39] - Integration of cross-modal tool fusion to expand application scenarios beyond text-based tools [39] - Development of efficient memory mechanisms for long-term tasks to reduce repetitive reasoning costs [39]

Core Insights - OpenAI achieved a significant milestone by enabling AI to reach gold medal level in the International Mathematical Olympiad (IMO) within just two months, showcasing a breakthrough in general AI technology [1][4][6] Group 1: Team and Methodology - The core team at OpenAI consisted of only three researchers who managed to accomplish what has been a long-standing goal in the AI field [4][10] - They utilized a technique called "multi-agent systems," allowing multiple AI "assistants" to work simultaneously, which facilitated the rapid resolution of complex problems [10][25] - The team employed external IMO medalists to evaluate the AI's proofs, ensuring a reliable assessment of its capabilities [1][6] Group 2: AI Capabilities and Performance - The AI demonstrated remarkable self-awareness by acknowledging its limitations, such as admitting when it could not solve the most challenging problems [18][19] - The breakthrough involved extending reasoning time from mere seconds to hours, enabling deeper thought processes for complex issues [6][23] - The AI's performance in the IMO was a significant leap from previous benchmarks, where it struggled with elementary math problems just a few years ago [12][15] Group 3: Implications and Future Directions - This achievement is seen as a stepping stone towards developing more advanced reasoning technologies that could eventually tackle unsolved problems in mathematics and science [6][25] - The team aims to integrate their methods into more OpenAI models, enhancing reasoning capabilities across various applications [27][29] - Future challenges include enabling AI to generate new mathematical problems, which would represent a significant advancement beyond mere problem-solving [28][29]

Core Insights - OpenAI claims that GPT-5 integrates "rapid response" and "deep reasoning" into a unified experience, enhancing capabilities in code generation, creative writing, multimodal abilities, and tool usage [1] - Despite these claims, there is no significant breakthrough in leading indicators for GPT-5, with user feedback indicating dissatisfaction due to the removal of older models without convincing alternatives [2] - Speculation arises that OpenAI's strategy may be shifting towards a more closed model system to drive stronger commercial monetization [3] Group 1: GPT-5 Core Upgrades - The most notable upgrade in GPT-5 is the enhancement of "reasoning integration," allowing for a one-stop solution that combines rapid response and deep reasoning [8] - OpenAI has invested heavily in post-training work, focusing on fine-tuning for both consumer and enterprise use, significantly improving the model's utility [9] - GPT-5 has made substantial advancements in code capabilities, setting new standards for reliability and practicality in software development [10][11] Group 2: Business and Infrastructure Perspective - OpenAI's ChatGPT currently boasts 700 million weekly active users, demonstrating the massive appeal of large model products [12] - 85% of ChatGPT's user base is located outside the United States, indicating its global reach and impact [12] - OpenAI has approximately 5 million paid enterprise users, showcasing rapid adoption across various industries [13] - The company has established a three-pronged business model consisting of personal subscriptions, enterprise services, and an API platform, all experiencing explosive growth [13] - OpenAI's CFO emphasizes the importance of input metrics like active user counts over traditional financial metrics, reflecting the company's mission to benefit humanity through AGI [14] Group 3: Product Experience Design Evolution - The discussion around benchmarks and rankings, particularly the ARC-AGI test, highlights the criticism of "score chasing" in AI development [21] - OpenAI's strategy focuses on delivering economic value through targeted optimization rather than blindly pursuing high scores on arbitrary benchmarks [23] Group 4: Multi-Agent System Implementation - The concept of multi-agent systems is gaining traction, with OpenAI exploring how multiple AI agents can collaborate to solve complex tasks more efficiently [24] - Real-world applications of multi-agent systems are being developed, such as using AI agents in software development to automate and streamline processes [25][26] - Challenges remain in fully realizing the potential of multi-agent systems, including the need for cultural and process changes within organizations [28] Group 5: OpenAI Technology Evolution - OpenAI's journey from GPT-1 to GPT-5 reflects a clear strategic progression, focusing on expanding model scale, enhancing alignment techniques, and building a comprehensive intelligent system [30][31] - Each generation of GPT has marked significant advancements in language capabilities, reliability, and practical applications, culminating in the widespread adoption of ChatGPT [33]

Application Trends - General-purpose Agent products are deeply integrating tool usage, capable of automating tasks that would take hours for humans, delivering richer content [1][13] - Computer Use Agents (CUA) are being pushed to market, focusing on visual operations and merging with text-based deep research Agents [1][14] - Vertical scenarios are accelerating Agentization, with natural language control becoming part of workflows, and AI programming gaining market validation with rapid revenue growth [1][15][17] Model Trends - Reasoning capabilities are continuously improving, with significant advancements in mathematical and coding problems, and some models performing excellently in international competitions [1][20] - Large model tools are enhancing their capabilities, integrating visual and text modalities, and improving multi-modal reasoning abilities [1][22] - Small models are accelerating in popularity, lowering deployment barriers, and model evaluation is evolving towards dynamic and practical task-oriented assessments [1][30] Technical Trends - Resource investment is shifting towards post-training and reinforcement learning, with the importance of reinforcement learning increasing, and future computing power consumption potentially exceeding pre-training [1][33] - Multi-agent systems are becoming a frontier paradigm, with online learning expected to be the next generation of learning methods, and rapid iteration and optimization of Transformer and hybrid architectures [1][33] - Code verification is emerging as a frontier for enhancing AI programming automation, with system prompts significantly impacting user experience [1][33] Industry Trends - xAI's Grok 4 has entered the global top tier, demonstrating that large models lack a competitive moat [2] - Computing power is becoming a key competitive factor, with leading players expanding their computing clusters to hundreds of thousands of cores [2] - OpenAI's leading advantage is diminishing as Google and xAI catch up, with the gap between Chinese and American general-purpose large models narrowing, and China showing strong performance in multi-modal fields [2]

Core Viewpoint - Inse Group (300781.SZ) aims to become a strategic partner for a leading domestic technology company in the marketing communication sector, supporting its global expansion through comprehensive marketing services provided by Inse Group and its subsidiaries [1] Group 1: Strategic Partnerships - The company is actively pursuing a strategic partnership with a major domestic technology firm to enhance its marketing communication capabilities [1] - This partnership is intended to assist the technology company in its global expansion efforts [1] Group 2: Research and Development Plans - Inse Group has established a new R&D plan, targeting the completion of a multi-agent system (MAS) foundation by Q3 [1] - The MAS will integrate various AI agents, including text, image, video, voice, and digital human components [1] - The company aims to develop an interactive mechanism and dynamic workflow platform to support efficient collaboration among AI agents [1]

Group 1 - The article discusses the value creation potential of AI agents in workflows that are difficult to automate using traditional methods [3]. - AI agents consist of three core components: models, tools, and instructions, which are essential for their functionality [6][8]. - The selection of models should be based on the complexity of tasks, with a focus on achieving performance benchmarks while optimizing for cost and latency [3][6]. Group 2 - Function calling is the primary method for large language models (LLMs) to interact with tools, enhancing the capabilities of AI agents [6][7]. - High-quality instructions are crucial for LLM-based applications, as they reduce ambiguity and improve decision-making [8][11]. - The orchestration of AI agents can be modeled as a graph, where agents represent nodes and tool calls represent edges, facilitating effective workflow execution [11][15]. Group 3 - The article outlines a supervisor mode for managing multiple specialized agents, allowing for task delegation and efficient workflow management [16][17]. - Custom handoff tools can be created to enhance the interaction between agents, allowing for tailored task assignments [33][34]. - The implementation of a multi-layered supervisory structure is possible, enabling the management of multiple teams of agents [31].