Core Insights - Google DeepMind's AlphaFold has significantly impacted protein structure prediction, driving advancements in scientific research over the past five years [1][4] - AI is reshaping scientific research, particularly in life sciences and biomedicine, due to rich data availability and urgent societal needs [1][3] Group 1: AI in Scientific Research - AI models and tools have achieved breakthroughs in basic research, including protein structure prediction and the discovery of new biological pathways [1][3] - The paradigm of "foundation models + research agents + autonomous laboratories" is emerging in AI-driven scientific research [3][13] Group 2: Advancements in Biology - DeepMind's AlphaFold has solved the protein structure prediction problem, earning the 2024 Nobel Prize in Chemistry and establishing itself as a digital infrastructure for modern biology [4] - The C2S-Scale model, developed by Google and Yale University, has generated new hypotheses about cancer cell behavior, showcasing AI's potential in formulating original scientific hypotheses [8] Group 3: AI in Drug Development - AI-assisted pathology detection has expanded to new disease scenarios, with the DeepGEM model achieving a prediction accuracy of 78% to 99% for lung cancer gene mutations [10] - The AI-optimized drug MTS-004 has completed Phase III clinical trials, marking a significant milestone in AI-driven drug discovery [10] Group 4: AI in Other Scientific Fields - AI applications in materials science are gaining momentum, with startups like Periodic Labs and CuspAI focusing on discovering new materials [11] - DeepMind's WeatherNext 2 model has surpassed traditional physical models in accuracy and efficiency for weather predictions [5] Group 5: Future of AI in Science - The evolution of scientific intelligence technologies is expected to accelerate, with AI foundational models and robotics enhancing research efficiency [19] - The integration of AI into scientific discovery is anticipated to lead to significant breakthroughs, with predictions of achieving near-relativistic level discoveries by 2028 [19]

Group 1: Global Innovation Landscape - China's cities are increasingly gaining advantages in the global innovation landscape, with 21 cities making it into the top 100 global innovation centers [1] - Beijing has ranked in the top three for four consecutive years, while the Guangdong-Hong Kong-Macau Greater Bay Area has risen to fourth place, and Shanghai is ranked tenth [1] - Beijing has topped the scientific center dimension for the first time, and the Greater Bay Area has moved up to second place in the innovation highland dimension [1] Group 2: Artificial Intelligence Conference - The 2025 International Artificial Intelligence Scientists Conference was held in Beijing, focusing on the evolution of AI from a research assistance tool to an "intelligent research partner" [2] - A new research intelligent system was launched, driven by "meta-scientific insights" and "scholar digital twins," aimed at supporting the full-process training of research talents [2] - The "meta-scientific insights" component helps the AI system understand scientific logic and predict research frontiers, while the "scholar digital twin" provides personalized support based on individual research styles [2] Group 3: AI Security Solutions - Green Alliance Technology Group has launched several AI security products, including a large model security assessment system and an AI security integrated machine [3] - The large model security assessment system automates deep scanning of mainstream models to identify risks such as adversarial attacks and data leaks [3] - The AI security integrated machine incorporates key capabilities like sensitive data leak prevention and refined computing resource scheduling, reflecting a trend towards integrating traditional security products with intelligent capabilities [3]

Core Insights - The article presents a comprehensive guide for constructing scientific agents based on large language models (LLMs), emphasizing the integration of AI in scientific research and addressing the epistemological and methodological gaps between AI and natural sciences [2][4]. Summary by Sections Overview of Scientific Agents - The guide aims to provide a structured approach to building scientific agents, detailing the levels of agent capabilities and construction strategies throughout the entire scientific research lifecycle [2][4]. Levels of Scientific Agents - Scientific agents are categorized into three levels: - **Agent as Assistant**: Limited to specific tasks within a domain, constructed using small models through post-training or fine-tuning, with high performance in specialized tasks but lacking comprehensive operational capabilities [8]. - **Agent as Partner**: Integrates various tools for enhanced capabilities, utilizing closed-source large models and modular design to independently perform tasks like literature consultation and hypothesis generation, though still limited in self-validation and reliability [8]. - **Agent as Avatar**: Focuses on multi-dimensional capability enhancement, featuring strong reasoning, memory, and collaboration skills, capable of providing comprehensive support across various research stages [8]. Construction Process of Scientific Agents - The construction process involves three main components: - **Knowledge Organization**: Structuring scientific information for effective understanding and reasoning, including unstructured sequences, structured data, instructions, and knowledge graphs [12][14]. - **Knowledge Injection**: Embedding domain-specific expertise into agents through explicit or implicit methods to enhance their problem-solving capabilities [12][14]. - **Tool Integration**: Expanding agent functionalities by incorporating external tools for specialized tasks, enabling autonomous operation and coordination of resources [12][14]. Capability Enhancement of Scientific Agents - Enhancements focus on: - **Memory Enhancement**: Essential for maintaining context and executing multi-step reasoning, utilizing various memory structures to support complex tasks [19]. - **Reasoning Enhancement**: Addressing limitations of LLMs through structured reasoning chains and domain-specific optimizations to improve output reliability [19]. - **Collaboration Enhancement**: Improving interactions between multi-agent systems and human researchers to optimize research outcomes [19]. Benchmarking and Evaluation - Benchmarks are categorized into knowledge-intensive and experiment-driven tasks, each emphasizing different aspects of scientific research processes [17][18]. - **Knowledge-Intensive Tasks**: Focus on complex, domain-specific tasks requiring deep expertise [17]. - **Experiment-Driven Tasks**: Evaluate the agent's ability to design and validate experiments autonomously [18]. Future Research Directions - Future efforts should focus on: - Ensuring empirical accuracy in scientific experiment designs and integrating verification tools [23]. - Designing flexible frameworks for complex task adaptation in specific research areas [23]. - Incorporating self-reflection and iterative mechanisms for continuous improvement [23]. - Optimizing interactions between agents and human researchers to enhance scientific discovery [23].

Core Viewpoint - Shanghai Jiao Tong University, Shanghai Algorithm Innovation Institute, and DeepMind Technology jointly launched the world's first general-purpose scientific research AI, SciMaster, based on the Innovator model [1] Group 1 - SciMaster integrates numerous specialized scientific tools and can generate "in-depth research reports" [1] - The AI supports a thinking chain editing function, allowing researchers to actively intervene in SciMaster's execution logic [1] - Researchers can modify task logic and content to achieve more accurate and reasonable research needs [1] Group 2 - SciMaster is now connected to the DeepModeling open-source community [1]