CatMaster: An Agentic Autonomous System for Computational Heterogeneous Catalysis Research

Density functional theory (DFT) is widely used to connect atomic structure with catalytic behavior, but computational heterogeneous catalysis studies often require long workflows that are costly, iterative, and sensitive to setup choices. Besides the intrinsic cost and accuracy limits of first-principles calculations, practical workflow issues such as keeping references consistent, preparing many related inputs, recovering from failed runs on computing clusters, and maintaining a complete record of what was done, can slow down projects and make results difficult to reproduce or extend. Here we present CatMaster, a large-language-model (LLM)-driven agent system that turns natural language requests into complete calculation workspaces, including structures, inputs, outputs, logs, and a concise run record. CatMaster maintains a persistent project record of key facts, constraints, and file pointers to support inspection and restartability. It is paired with a multi-fidelity tool library that covers rapid surrogate relaxations and high-fidelity DFT calculations for validation when needed. We demonstrate CatMaster on four demonstrations of increasing complexity: an O2 spin-state check with remote execution, BCC Fe surface energies with a protocol-sensitivity study and CO adsorption site ranking, high-throughput Pt--Ni--Cu alloy screening for hydrogen evolution reaction (HER) descriptors with surrogate-to-DFT validation, and a demonstration beyond the predefined tool set, including equation-of-state fitting for BCC Fe and CO-FeN4-graphene single-atom catalyst geometry preparation. By reducing manual scripting and bookkeeping while keeping the full evidence trail, CatMaster aims to help catalysis researchers focus on modeling choices and chemical interpretation rather than workflow management.

AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use

Machine learning-based interatomic potentials and force fields depend critically on accurate atomic structures, yet such data are scarce due to the limited availability of experimentally resolved crystals. Although atomic-resolution electron microscopy offers a potential source of structural data, converting these images into simulation-ready formats remains labor-intensive and error-prone, creating a bottleneck for model training and validation. We introduce AutoMat, an end-to-end, agent-assisted pipeline that automatically transforms scanning transmission electron microscopy (STEM) images into atomic crystal structures and predicts their physical properties. AutoMat combines pattern-adaptive denoising, physics-guided template retrieval, symmetry-aware atomic reconstruction, fast relaxation and property prediction via MatterSim, and coordinated orchestration across all stages. We propose the first dedicated STEM2Mat-Bench for this task and evaluate performance using lattice RMSD, formation energy MAE, and structure-matching success rate. By orchestrating external tool calls, AutoMat enables a text-only LLM to outperform vision-language models in this domain, achieving closed-loop reasoning throughout the pipeline. In large-scale experiments over 450 structure samples, AutoMat substantially outperforms existing multimodal large language models and tools. These results validate both AutoMat and STEM2Mat-Bench, marking a key step toward bridging microscopy and atomistic simulation in materials science.The code and dataset are publicly available at https://github.com/yyt-2378/AutoMat and https://huggingface.co/datasets/yaotianvector/STEM2Mat.

MatWheel: Addressing Data Scarcity in Materials Science Through Synthetic Data

Data scarcity and the high cost of annotation have long been persistent challenges in the field of materials science. Inspired by its potential in other fields like computer vision, we propose the MatWheel framework, which train the material property prediction model using the synthetic data generated by the conditional generative model. We explore two scenarios: fully-supervised and semi-supervised learning. Using CGCNN for property prediction and Con-CDVAE as the conditional generative model, experiments on two data-scarce material property datasets from Matminer database are conducted. Results show that synthetic data has potential in extreme data-scarce scenarios, achieving performance close to or exceeding that of real samples in all two tasks. We also find that pseudo-labels have little impact on generated data quality. Future work will integrate advanced models and optimize generation conditions to boost the effectiveness of the materials data flywheel.

Accelerating High-Efficiency Organic Photovoltaic Discovery via Pretrained Graph Neural Networks and Generative Reinforcement Learning

Organic photovoltaic (OPV) materials offer a promising avenue toward cost-effective solar energy utilization. However, optimizing donor-acceptor (D-A) combinations to achieve high power conversion efficiency (PCE) remains a significant challenge. In this work, we propose a framework that integrates large-scale pretraining of graph neural networks (GNNs) with a GPT-2 (Generative Pretrained Transformer 2)-based reinforcement learning (RL) strategy to design OPV molecules with potentially high PCE. This approach produces candidate molecules with predicted efficiencies approaching 21\%, although further experimental validation is required. Moreover, we conducted a preliminary fragment-level analysis to identify structural motifs recognized by the RL model that may contribute to enhanced PCE, thus providing design guidelines for the broader research community. To facilitate continued discovery, we are building the largest open-source OPV dataset to date, expected to include nearly 3,000 donor-acceptor pairs. Finally, we discuss plans to collaborate with experimental teams on synthesizing and characterizing AI-designed molecules, which will provide new data to refine and improve our predictive and generative models.

MoMa: A Modular Deep Learning Framework for Material Property Prediction

Deep learning methods for material property prediction have been widely explored to advance materials discovery. However, the prevailing pre-train then fine-tune paradigm often fails to address the inherent diversity and disparity of material tasks. To overcome these challenges, we introduce MoMa, a Modular framework for Materials that first trains specialized modules across a wide range of tasks and then adaptively composes synergistic modules tailored to each downstream scenario. Evaluation across 17 datasets demonstrates the superiority of MoMa, with a substantial 14% average improvement over the strongest baseline. Few-shot and continual learning experiments further highlight MoMa's potential for real-world applications. Pioneering a new paradigm of modular material learning, MoMa will be open-sourced to foster broader community collaboration.

ErgoChat: a Visual Query System for the Ergonomic Risk Assessment of Construction Workers

In the construction sector, workers often endure prolonged periods of high-intensity physical work and prolonged use of tools, resulting in injuries and illnesses primarily linked to postural ergonomic risks, a longstanding predominant health concern. To mitigate these risks, researchers have applied various technological methods to identify the ergonomic risks that construction workers face. However, traditional ergonomic risk assessment (ERA) techniques do not offer interactive feedback. The rapidly developing vision-language models (VLMs), capable of generating textual descriptions or answering questions about ergonomic risks based on image inputs, have not yet received widespread attention. This research introduces an interactive visual query system tailored to assess the postural ergonomic risks of construction workers. The system's capabilities include visual question answering (VQA), which responds to visual queries regarding workers' exposure to postural ergonomic risks, and image captioning (IC), which generates textual descriptions of these risks from images. Additionally, this study proposes a dataset designed for training and testing such methodologies. Systematic testing indicates that the VQA functionality delivers an accuracy of 96.5%. Moreover, evaluations using nine metrics for IC and assessments from human experts indicate that the proposed approach surpasses the performance of a method using the same architecture trained solely on generic datasets. This study sets a new direction for future developments in interactive ERA using generative artificial intelligence (AI) technologies.

KULTURE Bench: A Benchmark for Assessing Language Model in Korean Cultural Context

Large language models have exhibited significant enhancements in performance across various tasks. However, the complexity of their evaluation increases as these models generate more fluent and coherent content. Current multilingual benchmarks often use translated English versions, which may incorporate Western cultural biases that do not accurately assess other languages and cultures. To address this research gap, we introduce KULTURE Bench, an evaluation framework specifically designed for Korean culture that features datasets of cultural news, idioms, and poetry. It is designed to assess language models' cultural comprehension and reasoning capabilities at the word, sentence, and paragraph levels. Using the KULTURE Bench, we assessed the capabilities of models trained with different language corpora and analyzed the results comprehensively. The results show that there is still significant room for improvement in the models' understanding of texts related to the deeper aspects of Korean culture.

Enhanced forecasting of stock prices based on variational mode decomposition, PatchTST, and adaptive scale-weighted layer

The significant fluctuations in stock index prices in recent years highlight the critical need for accurate forecasting to guide investment and financial strategies. This study introduces a novel composite forecasting framework that integrates variational mode decomposition (VMD), PatchTST, and adaptive scale-weighted layer (ASWL) to address these challenges. Utilizing datasets of four major stock indices--SP500, DJI, SSEC, and FTSE--from 2000 to 2024, the proposed method first decomposes the raw price series into intrinsic mode functions (IMFs) using VMD. Each IMF is then modeled with PatchTST to capture temporal patterns effectively. The ASWL module is applied to incorporate scale information, enhancing prediction accuracy. The final forecast is derived by aggregating predictions from all IMFs. The VMD-PatchTST-ASWL framework demonstrates significant improvements in forecasting accuracy compared to traditional models, showing robust performance across different indices. This innovative approach provides a powerful tool for stock index price forecasting, with potential applications in various financial analysis and investment decision-making contexts.

Large Language Model assisted End-to-End Network Health Management based on Multi-Scale Semanticization

Network device and system health management is the foundation of modern network operations and maintenance. Traditional health management methods, relying on expert identification or simple rule-based algorithms, struggle to cope with the dynamic heterogeneous networks (DHNs) environment. Moreover, current state-of-the-art distributed anomaly detection methods, which utilize specific machine learning techniques, lack multi-scale adaptivity for heterogeneous device information, resulting in unsatisfactory diagnostic accuracy for DHNs. In this paper, we develop an LLM-assisted end-to-end intelligent network health management framework. The framework first proposes a Multi-Scale Semanticized Anomaly Detection Model (MSADM), incorporating semantic rule trees with an attention mechanism to address the multi-scale anomaly detection problem in DHNs. Secondly, a chain-of-thought-based large language model is embedded in downstream to adaptively analyze the fault detection results and produce an analysis report with detailed fault information and optimization strategies. Experimental results show that the accuracy of our proposed MSADM for heterogeneous network entity anomaly detection is as high as 91.31\%.

Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering

This paper presents a study on the integration of domain-specific knowledge in prompt engineering to enhance the performance of large language models (LLMs) in scientific domains. A benchmark dataset is curated to encapsulate the intricate physical-chemical properties of small molecules, their drugability for pharmacology, alongside the functional attributes of enzymes and crystal materials, underscoring the relevance and applicability across biological and chemical domains.The proposed domain-knowledge embedded prompt engineering method outperforms traditional prompt engineering strategies on various metrics, including capability, accuracy, F1 score, and hallucination drop. The effectiveness of the method is demonstrated through case studies on complex materials including the MacMillan catalyst, paclitaxel, and lithium cobalt oxide. The results suggest that domain-knowledge prompts can guide LLMs to generate more accurate and relevant responses, highlighting the potential of LLMs as powerful tools for scientific discovery and innovation when equipped with domain-specific prompts. The study also discusses limitations and future directions for domain-specific prompt engineering development.