20 papers · ranked by Valyu relevance
Sanderson Oliveira de Macedo
AI tools for programming are no longer just autocomplete or chat assistants: they organize themselves as development frameworks, with process, roles, artifacts and verification. Recent surveys map agents and LLMs for software engineering, but a study centered on the operational frameworks that turn these capabilities…
Guy Hutton, Sue Coates, Stuart Gilmour, Jimmy T. Efird
An improved understanding of the sanitation enabling environment and status of market development (“sanitation economy”) is crucial not only for advancing national and global sanitation goals, but also for attracting the financing necessary to drive meaningful progress in low- and middle-income countries (LMICs). This…
Authors not listed
Self-driving laboratories (SDLs) promise accelerated scientific discovery and product development by closing the loop between robotic execution and AI/ML-driven decision making. In practice, however, SDL orchestration remains fragmented; workflows are typically encoded as laboratory-specific scripts or bespoke…
Aaron Simpson, Ben Jackson, Michael Rosenberg, Claire Willis
3## Application of the framework The Healthway Evaluation Framework has to date been (and is being) implemented by State Sporting Associations and peak bodies for the evaluation of health promotion initiatives-targeted at key health areas including mental health and healthy eating-reaching over 150,000 people in…
Shreyansh Agrawal, Harsh B. Anadkat, Kiran K. Athimoolam, Harsh Bhardwaj + 8 more
Recent advances in artificial intelligence (AI) have prompted claims about autonomous “AI scientists,” yet systematic evaluations of these capabilities remain scarce. This exploratory study investigates whether current AI frameworks can execute scientific research tasks beyond isolated demonstrations. We tested eight…
Calder Robbins, Hyoungseo Son, Chun Kwang Tan, Cheryl Wang + 6 more
Physical human-device interaction is central to many emerging technologies in neurorehabilitation and assistive robotics, but simulation-based research in this area remains fragmented across musculoskeletal models, assistive-device representations, task definitions, and controller-development work-flows. This…
Rainer Mere, Merike Sisask, Peeter Värnik, Chantal Van Audenhove + 1 more
The development of our framework typology followed an iterative, inductive process. Initial extraction captured the specific framework names as reported by study authors. Through iterative review, we grouped frameworks into categories based on their theoretical roots, stated purposes, and level of analysis. Initial…
Authors not listed
Metal–organic frameworks (MOFs) feature a rich structural diversity, including crystalline, amorphous, and liquid phases of varying topologies. Their structural characterization is often performed either at the local scale (through pair distribution functions, bond angle distributions, etc.) or, for crystalline phases…
Elizabeth B. Vaughan, Josephine Bicknell, Henry Holleb, Kodinna Anachebe + 2 more
Outcomes: The Structure and Function of Deficit and Anti-deficit Framing and Their Relevance to Chemistry Education Authors: Elizabeth B. Vaughan, Josephine Bicknell, Henry Holleb, Kodinna Anachebe, Tia Kledzik, Nicole M. James The existence of differential educational outcomes as a function of students’ background is…
Olivia A. King, Ella Ottrey, Michele Conlin, Sze Lin Yoong + 5 more
Background Building research capacity in health settings is essential for improving the relevance and application of health research. Rigorous evaluation of research capacity in health settings optimizes the development, implementation and improvement of such initiatives. Cooke’s 2005 framework was the earliest…
Susanne Göbel, Ralf Lämmel
Graphical model editing is shifting from desktop applications to web-based tools. We analyze the characteristics of existing frameworks and, based on this analysis, we derive a set of design principles that imply low-effort generation, extensive customization possibilities, and straightforward deployment of the…
Gianluca Quargnali, Pablo Rivera-Fuentes
Deep learning methods for protein structure generation, sequence design, and structure and property prediction have created unprecedented opportunities for protein engineering and drug discovery. However, using these tools often requires navigating incompatible software environments, diverse input/output formats, and…
Hu Wei
AI agent systems increasingly rely on reusable non-LLM engineering infrastructure that packages tool mediation, context handling, delegation, safety control, and orchestration. Yet the architectural design decisions in this surrounding infrastructure remain understudied. This paper presents a protocol-guided…
Yunchao Wang, Sun, Guodao, Zihang Fu + 5 more
—With the advancement of natural language generation (NLG) technologies, creative story generation systems have gained increasing attention. However, current systems often fail to accurately translate user intent into satisfactory story outputs due to a lack of fine-grained control and unclear input specifications…
Mohammed O. Ahmed, Sahil A. Amale, Rhythm D. Bhavsar, Pratham Chopra + 18 more
Artificial Intelligence (AI) frameworks for automating scientific research have shown strong performance on benchmarks, but their capacity to routinely reproduce results from multiple real-life published studies remains largely untested. We evaluated five advanced AI research frameworks (Kosmos, K-Dense, ToolUniverse…
Benjamin M. David, Paul A. Jensen
Coordinating multiple liquid handling robots is a complex logistical task when designing biological experiments. Protocol designers must consider the capabilities and constraints of each robot to distribute work optimally across multiple instruments. We developed an optimization framework that finds optimal liquid…
Authors not listed
This comprehensive review examines the evolution of autonomous materials synthesis laboratories that integrate artificial intelligence with advanced robotics to accelerate discovery. Traditional materials development pipelines typically require 10-20 years, but self-driving laboratories (SDLs) and Materials…
Authors not listed
AI-driven molecular generation encounters a "generation-synthesis gap": most computationally designed molecules cannot be synthesized in laboratories, limiting AI-assisted drug design (AIDD) applications. Current approaches to assess synthetic accessibility (SA) include computer-aided synthesis planning (CASP) tools…
Authors not listed
Current methods for predicting molecular porous materials typically exploit prior knowledge of similar systems, which biases the final outcome to a limited exploration space. To design novel structures and materials, the community must be able to evaluate and model all candidates without any bias. In this paper, we…
Wei Minn, Biniam Fisseha Demissie, Yan Naing Tun, Jiakun Liu + 3 more
Automated GUI testing is crucial for ensuring the quality and reliability of Android apps. However, the efficacy of existing UI testing techniques is often limited, especially in terms of coverage. Recent studies, including the state-of-the-art, struggle to achieve more than 30% activity coverage in real-world apps.…