Related papers: OSCAgent: Accelerating the Discovery of Organic So…

Organic solar cells (OSCs) containing an active layer consisting of a nanostructured blend of a conjugated polymer like poly(3-hexylthiophene) (P3HT) and an electron acceptor molecule have the potential of competing against silicon-based…

Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models often struggle with novel and specialized software,…

Foundation models are becoming valuable tools in medicine. Yet despite their promise, the best way to leverage Large Language Models (LLMs) in complex medical tasks remains an open question. We introduce a novel multi-agent framework, named…

Usability testing is a fundamental research method that user experience (UX) researchers use to evaluate and iterate their new designs. But what about evaluating and iterating the usability testing study design itself? Recent advances in…

Identifying transition states (TSs) on potential energy surfaces is a central computational bottleneck in mechanistic studies of catalytic materials. A TS search is not a single calculation but a long-horizon, multi-step workflow of…

We present a highly efficient workflow for designing semiconductor structures with specific physical properties, which can be utilized for a range of applications, including photocatalytic water splitting. Our algorithm generates candidate…

Large language model (LLM)-based computer-use agents represent a convergence of AI and OS capabilities, enabling natural language to control system- and application-level functions. However, due to LLMs' inherent uncertainty issues,…

Over the last two decades the organic solar cell community has synthesised tens of thousands of novel polymers and small molecules in the search for an optimum light harvesting material. These materials were often crudely evaluated simply…

We present MOSAIC, a multi-agent Large Language Model (LLM) framework for solving challenging scientific coding tasks. Unlike general-purpose coding, scientific workflows require algorithms that are rigorous, interconnected with deep domain…

Chalcogenide perovskites have emerged as promising absorber materials for next-generation photovoltaic devices, yet their experimental realization remains limited by competing phases, structural polymorphism, and synthetic challenges. Here,…

There has been unprecedented interest in developing agents that expand the boundary of scientific discovery, primarily by optimizing quantitative objective functions specified by scientists. However, for grand challenges in science, these…

Oral Squamous Cell Carcinoma (OSCC) is a prevalent and aggressive malignancy where deep learning-based computer-aided diagnosis and prognosis can enhance clinical assessments.However, existing publicly available OSCC datasets often suffer…

Background: The surge in single-cell omics data exposes limitations in traditional, manually defined analysis workflows. AI agents offer a paradigm shift, enabling adaptive planning, executable code generation, traceable decisions, and…

Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration…

High charge mobility in active layers of organic electronic devices is often necessary for their efficient operation. As a result, search for high-mobility materials among the plethora of synthesizable organic semiconductors is of paramount…

Earth observation (EO) is essential for understanding the evolving states of the Earth system. Although recent MLLMs have advanced EO research, they still lack the capability to tackle complex tasks that require multi-step reasoning and the…

Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to…

High-quality code documentation is crucial for software development especially in the era of AI. However, generating it automatically using Large Language Models (LLMs) remains challenging, as existing approaches often produce incomplete,…

Large Vision-Language Models (VLMs) have demonstrated significant potential on complex visual understanding tasks through iterative optimization methods.However, these models generally lack effective self-correction mechanisms, making it…

Large language models (LLMs) excel at natural language tasks but are limited by their static parametric knowledge, especially in knowledge-intensive task. Retrieval-augmented generation (RAG) mitigates this by integrating external…