Tokyo 152 - 8552, Japan E - mail: kan.hatakeyama [ [ at ] ] weblab.t.u - tokyo.ac.jp Abstract This review explores the potential of foundation models to advanc e laboratory automation in the materials and chemical sciences. It emphasizes the dual roles of these models: cognitive functions for experimental planning and data analysis, and physical functions for hardware operations. While traditional laboratory automation has relied heavily on specialized, rigid systems, foundation models offer adaptability through their general - purpose intelligence and multimodal capabilities. Recent advancements have demonstrated the fea sibility of using large language models (LLMs) and multimodal robotic systems to handle complex and dynamic laboratory tasks. However, significant challenges remain, including precision manipulation of hardware, integration of multimodal data, and ensuring operational safety. Th is paper outlines a roadmap highlighting future directions, advocating for close interdisciplinary collaboration, benchmark establishment, and strategic human - AI integration to realize fully autonomous experimental laboratories. Keywords Laboratory Automation; Foundation Models; Robotics; Artificial Intelligence; Materials Science 1. Expectations for Foundation Models in Materials Laboratory Automation Laboratory automation, a technology aimed at automating experimental research, is expected to pave the way for a new research paradigm in materials science [1, 2, 3] . By rapidly and comprehensively executing numerous experiments, laboratory automation accelerates research, enhances reproducibility through precisely controlled robotic processes, and enables swift and distributed knowledge sharing among researchers worldwide [1] . This technology is anticipated to contribute significantly to the development of crucial devices and compounds, including catalyst s for energy and chemical conversions, environmentally friendly plastics, solar cells, secondary batteries, fuel cells, thermoelectric conversion modules, nuclear fusion reactors, quantum computers, and energy - efficient computing systems [1, 4, 5] . The success of next - generation laboratory automation depends not only o n experimental hardware but also o n the utilization of artificial intelligence (AI), especially foundation models. Foundation models represent a new AI paradigm encompassing large language models like GPT - 4 [6], multimodal models, and agent - related technologies. These foundation models and generative AI have begun to influenc e chemistry and materials science [7], giving rise to diverse applications including molecular and materials design [8, 9, 10], reaction pathway exploration [11], catalyst design [12], and even autonomous planning of chemical experiments [13] . Additionally, foundation models are being expanded to hardware control mechanisms, enabling natural language - driven robotic operations [14, 15] .

In this research paper, we propose a new type of energy-efficient Green AI architecture to support circular economies and address the contemporary challenge of sustainable resource consumption in modern systems. We introduce a multi-layered framework and meta-architecture that integrates state-of-the-art machine learning algorithms, energy-conscious computational models, and optimization techniques to facilitate decision-making for resource reuse, waste reduction, and sustainable production.We tested the framework on real-world datasets from lithium-ion battery recycling and urban waste management systems, demonstrating its practical applicability. Notably, the key findings of this study indicate a 25 percent reduction in energy consumption during workflows compared to traditional methods and an 18 percent improvement in resource recovery efficiency. Quantitative optimization was based on mathematical models such as mixed-integer linear programming and lifecycle assessments. Moreover, AI algorithms improved classification accuracy on urban waste by 20 percent, while optimized logistics reduced transportation emissions by 30 percent. We present graphical analyses and visualizations of the developed framework, illustrating its impact on energy efficiency and sustainability as reflected in the simulation results. This paper combines the principles of Green AI with practical insights into how such architectural models contribute to circular economies, presenting a fully scalable and scientifically rooted solution aligned with applicable UN Sustainability Goals worldwide. These results open avenues for incorporating newly developed AI technologies into sustainable management strategies, potentially safeguarding local natural capital while advancing technological progress.

Precision process planning in Computer Numerical Control (CNC) machining demands rapid, context-aware decisions on tool selection, feed-speed pairs, and multi-axis routing, placing immense cognitive and procedural burdens on engineers from design specification through final part inspection. Conventional rule-based computer-aided process planning and knowledge-engineering shells freeze domain know-how into static tables, which become limited when dealing with unseen topologies, novel material states, shifting cost-quality-sustainability weightings, or shop-floor constraints such as tool unavailability and energy caps. Large language models (LLMs) promise flexible, instruction-driven reasoning for tasks but they routinely hallucinate numeric values and provide no provenance. We present Augmented Retrieval Knowledge Network Enhanced Search & Synthesis (ARKNESS), the end-to-end framework that fuses zero-shot Knowledge Graph (KG) construction with retrieval-augmented generation to deliver verifiable, numerically exact answers for CNC process planning. ARKNESS (1) automatically distills heterogeneous machining documents, G-code annotations, and vendor datasheets into augmented triple, multi-relational graphs without manual labeling, and (2) couples any on-prem LLM with a retriever that injects the minimal, evidence-linked subgraph needed to answer a query. Benchmarked on 155 industry-curated questions spanning tool sizing and feed-speed optimization, a lightweight 3B-parameter Llama-3 augmented by ARKNESS matches GPT-4o accuracy while achieving a +25 percentage point gain in multiple-choice accuracy, +22.4 pp in F1, and 8.1x ROUGE-L on open-ended responses.

While language models are increasingly utilized in materials science, typical models rely on frequency-centric tokenization methods originally developed for natural language processing. However, these methods frequently produce excessive fragmentation and semantic loss, failing to maintain the structural and semantic integrity of material concepts. To address this issue, we propose MATTER, a novel tokenization approach that integrates material knowledge into tokenization. Based on MatDetector trained on our materials knowledge base and a re-ranking method prioritizing material concepts in token merging, MATTER maintains the structural integrity of identified material concepts and prevents fragmentation during tokenization, ensuring their semantic meaning remains intact. The experimental results demonstrate that MATTER outperforms existing tokenization methods, achieving an average performance gain of $4\%$ and $2\%$ in the generation and classification tasks, respectively. These results underscore the importance of domain knowledge for tokenization strategies in scientific text processing. Our code is available at https://github.com/yerimoh/MATTER

In this paper, a compressed air-actuated soft robotic module was developed by incorporating a shape memory alloy (SMA) wire into its structure to achieve the desired bending angle with greater precision. First, a fiber-reinforced bending module with a strain-limiting layer made of polypropylene was fabricated. The SMA wire was then placed in a silicon matrix, which was used as a new strain-limiting layer. A simple closed-loop control algorithm was used to regulate the bending angle of the soft robot within its workspace. A camera was utilized to measure the angular changes in the vertical plane. Different angles, ranging from 0 to 65 degrees, were covered to evaluate the performance of the module and the bending angle control algorithm. The experimental tests demonstrate that using the SMA wire results in more precise control of bending in the vertical plane. In addition, it is possible to bend more with less working pressure. The error range was reduced from an average of 5 degrees to 2 degrees, and the rise time was reduced from an average of 19 seconds to 3 seconds.

Recent advances in Foundation Models for Materials Science are poised to revolutionize the discovery, manufacture, and design of novel materials with tailored properties and responses. Although great strides have been made, successes have been restricted to materials classes where multi-million sample data repositories can be readily curated (e.g., atomistic structures). Unfortunately, for many structural and functional materials (e.g., mesoscale structured metal alloys), such datasets are too costly or prohibitive to construct; instead, datasets are limited to very few examples. To address this challenge, we introduce a novel machine learning approach for learning from hyper-sparse, complex spatial data in scientific domains. Our core contribution is a physics-driven data augmentation scheme that leverages an ensemble of local generative models, trained on as few as five experimental observations, and coordinates them through a novel diversity curation strategy to generate a large-scale, physically diverse dataset. We utilize this framework to construct PolyMicros, the first Foundation Model for polycrystalline materials (a structural material class important across a broad range of industrial and scientific applications). We demonstrate the utility of PolyMicros by zero-shot solving several long standing challenges related to accelerating 3D experimental microscopy. Finally, we make both our models and datasets openly available to the community.

The renewed U.S.-China trade truce struck in London left a key area of export restrictions tied to national security untouched, an unresolved conflict that threatens a more comprehensive deal, two people briefed on detailed outcomes of the talks have said. Beijing has not committed to grant export clearance for some specialized rare-earth magnets that U.S. military suppliers need for fighter jets and missile systems, the people said. The United States maintains export curbs on China's purchases of advanced artificial intelligence chips out of concern that they also have military applications. At talks in London last week, China's negotiators appeared to link progress in lifting export controls on military-use rare earth magnets with the longstanding U.S. curbs on exports of the most advanced AI chips to China. That marked a new twist in trade talks that began with opioid trafficking, tariff rates and China's trade surplus, but have since shifted to focus on export controls.

Enzymes are important proteins that catalyze chemical reactions. In recent years, machine learning methods have emerged to predict enzyme function from sequence; however, there are no standardized benchmarks to evaluate these methods. We introduce CARE, a benchmark and dataset suite for the Classification And Retrieval of Enzymes (CARE). CARE centers on two tasks: (1) classification of a protein sequence by its enzyme commission (EC) number and (2) retrieval of an EC number given a chemical reaction. For each task, we design train-test splits to evaluate different kinds of out-of-distribution generalization that are relevant to real use cases. For the classification task, we provide baselines for state-of-the-art methods. Because the retrieval task has not been previously formalized, we propose a method called Contrastive Reaction-EnzymE Pretraining (CREEP) as one of the first baselines for this task and compare it to the recent method, CLIPZyme. CARE is available at https://github.com/jsunn-y/CARE/.

Safely aligning large language models (LLMs) often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on complex iterative prompting or auxiliary models. To address this, we introduce Refusal-Aware Adaptive Injection (RAAI), a straightforward, training-free, and model-agnostic framework that repurposes LLM attack techniques. RAAI works by detecting internal refusal signals and adaptively injecting predefined phrases to elicit harmful, yet fluent, completions. Our experiments show RAAI effectively jailbreaks LLMs, increasing the harmful response rate from a baseline of 2.15% to up to 61.04% on average across four benchmarks. Crucially, fine-tuning LLMs with the synthetic data generated by RAAI improves model robustness against harmful prompts while preserving general capabilities on standard tasks like MMLU and ARC. This work highlights how LLM attack methodologies can be reframed as practical tools for scalable and controllable safety alignment.

Synthetic polymeric materials underpin fundamental technologies in the energy, electronics, consumer goods, and medical sectors, yet their development still suffers from prolonged design timelines. Although polymer informatics tools have supported speedup, polymer simulation protocols continue to face significant challenges in the on-demand generation of realistic 3D atomic structures that respect conformational diversity. Generative algorithms for 3D structures of inorganic crystals, bio-polymers, and small molecules exist, but have not addressed synthetic polymers because of challenges in representation and dataset constraints. In this work, we introduce polyGen, the first generative model designed specifically for polymer structures from minimal inputs such as the repeat unit chemistry alone. polyGen combines graph-based encodings with a latent diffusion transformer using positional biased attention for realistic conformation generation. Given the limited dataset of 3,855 DFT-optimized polymer structures, we incorporate joint training with small molecule data to enhance generation quality. We also establish structure matching criteria to benchmark our approach on this novel problem. polyGen overcomes the limitations of traditional crystal structure prediction methods for polymers, successfully generating realistic and diverse linear and branched conformations, with promising performance even on challenging large repeat units. As the first atomic-level proof-of-concept capturing intrinsic polymer flexibility, it marks a new capability in material structure generation.