24 papers · ranked by Valyu relevance
Kehao Mao, Baokun Hu, Ruixin Lin, Zewen Li + 2 more
Automated programming has become a powerful tool for solving real-world problems. Code generation, in particular, plays a key role in improving developer productivity and reducing the entry barrier to software development. Recent advances in large language models (LLMs) have significantly improved program synthesis…
Qian Xiong, Bo Yang, Weisong Sun, Yiran Zhang + 3 more
—Automated code generation driven by Large Language Models (LLMs) has enhanced development efficiency, yet generating complex application-level software code remains challenging. Multi-agent frameworks show potential, but existing methods perform inadequately in large-scale application-level software code generation…
Yutao Chen, Xingwei Zhou, Wenshan Hu, Bo Zhao + 1 more
Unmanned Underwater Vehicle (UUV) swarms have become increasingly crucial for underwater exploration and applications, where their coordinated operation offers significant advantages over single-vehicle systems. However, unlike single-vehicle systems, the development of swarm control systems is more complicated…
Authors not listed
Bayesian optimization (BO) has become increasingly important for experimental optimization across scientific domains, yet implementing BO pipelines requires significant programming expertise and familiarity with specialized frameworks. This creates a barrier for domain experts who could benefit from BO but lack the…
Dawei Yuan, Guojun Liang, Tingting Li, Suping Liu
We present a reinforcement learning framework that enhances natural language queries to improve DeepSeek code generation. A parametric refiner (Qwen with LoRA) is trained via REINFORCE while the generator remains fixed, using a scalar reward that can combine text similarity (BLEU-4, ROUGE-L, F1, Overlap) with execution…
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…
Xinyu Shi, Zhou Yang, An Ran Chen
Behavior-Driven Development (BDD) helps technical and non-technical stakeholders share a common understanding of software requirements through natural-language scenarios. Glue code makes these scenarios executable by mapping each step to the corresponding project code. However, developing and maintaining glue code…
Muhammad Zain Butt, Rana Sheraz Ahmad, Eman Fatima, Muhammad Tahir ul Qamar
The application of Large Language Models (LLMs) for generating data visualizations through natural language interaction represents a promising advance in AI-assisted scientific analysis. However, existing LLM-based tools largely emphasize graph generation, while research workflows require not only visualization but…
Mohamed Mamdouh, Ahmed Khalid, Reem Mahmoud, Osama Desouki + 1 more
This paper addresses a critical challenge in Printed Circuit Board (PCB) manufacturing by proposing an AI-driven, fully automated drilling machine that employs sophisticated path-planning techniques. Current methodologies often fail to adequately assess designs with varying hole sizes, diverse component placements, and…
Syed Mohammad Kashif, Ruiyin Li, Peng Liang, Amjed Tahir + 3 more
New generation of AI coding tools, including AI-powered IDEs equipped with agentic capabilities, can generate code within the context of the project. These AI IDEs are increasingly perceived as capable of producing project-level code at scale. However, there is limited empirical evidence on the extent to which they can…
Liu, Jingyao, Huang, Chen + 6 more
The rapid advancement in large language models (LLMs) has demonstrated significant potential in End-to-End Software Development (E2ESD). However, existing E2ESD benchmarks are limited by coarse-grained requirement specifications and unreliable evaluation protocols, hindering a true understanding of current framework…
Hyeon-Min Kim, Hwayeon Jeong, Abyot Melkamu Mekonnen, Yeongjun Kim + 4 more
Large language models (LLMs) are increasingly used to generate bioinformatics pipelines and to carry out analyses from natural-language prompts. However, the resulting analyses are often difficult to reproduce across sessions, owing to the non-deterministic nature of LLM-driven conversations and heterogeneity of local…
Mamdouh Alenezi
Large language models (LLMs) and agentic AI are shifting software engineering from manual coding toward intent specification, architecture, and governance. Two paradigms have emerged: vibe coding, an intuition-driven approach accepting AI artifacts via observed behavior, and Specification-Driven Development (SDD)…
Ihsan Tolga Medeni, Metehan Ünal, Roberto Galizi, Bryan Bartley + 4 more
Large language models have transformed software engineering practices. However, generated artefacts are not always developer-friendly and may partially meet complex requirements. As the need to standardise, integrate, and develop tools in engineering biology increases, novel approaches are needed to create and maintain…
Rong Huang, Su Tao
Automated Machine Learning (AutoML) aims to streamline the end-to-end process of ML models, yet current approaches remain constrained by rigid rule-based frameworks and structured input requirements that create barriers for non-expert users. Despite advances in Large Language Models (LLMs) demonstrating capabilities in…
Youjia Ma, Bo-Wei Han, Minzhe Zhang, Yang Leng + 3 more
The rapid expansion of biomedical data necessitates efficient bioinformatics tools, yet conventional workflows rely heavily on manual dependencies, hindering scalability and broader adoption. Building on the foundation of ToolsGenie 1.0, we introduce ToolsGenie 2.0, a multi-agent AI framework that automates…
Xiaopeng Xu, Chenjie Feng, Chao Zha, Wenjia He + 3 more
Computational protein design is often constrained by slow, complex, inaccessible, and highly sophiscated and expert-dependent workflows that hinder its transferrability and generalization power for broader applications. We present ProteinMCP, an agentic AI framework designed to accelerate and democratize protein…
Hung Q. Vo, Huy Q. Vo, Son T. Ly, Zhihao Wan + 5 more
Conventional tissue image analysis software provides foundational capabilities for cellular analysis, including segmentation, basic morphological feature extraction, and spatial organization analysis. However, these tools often require manual intervention and are not well integrated with code-driven automation…
Authors not listed
We provide an overview of core molSimplify functionality and recent updates that enhance its capabilities for automated molecular and materials modeling. We describe the mol3D and atom3D classes, which store atomic and bonding information for a wide range of functions, including reading, modifying, and characterizing…
Julius Irion, Moritz Leugers, Paul Hartwig, Simon Kling + 4 more
AI-assisted development tools enable rapid prototyping of services but often lack awareness of architectural constraints, infrastructure dependencies, and organizational standards required in production environments. Consequently, generated artifacts may exhibit brittle behavior and limited deployability. We propose a…
Mohammad M. Abdellatif, Osama Desouki, Mohamed AbdelRaheem
Network automation is an emerging technology which gained a lot of traction over the past few years. NA can be used at multiple levels, such as topology creation, configuration generation, and testing. It can save a great amount of time and effort compared to conventional ways. Here, the automated topology creation…
Baris Ardic, Quentin Le Dilavrec, Andy Zaidman
The integration of generative AI tools like ChatGPT into software engineering workflows opens up new opportunities to boost productivity in tasks such as unit test engineering. However, these AI-assisted workflows can also significantly alter the developer’s role, raising concerns about control, output quality, and…
Authors not listed
Bridging AI and self-driving laboratories, we introduce the first fully-automated, closed-loop molecular discovery cycle, exemplified by the identification of novel JAK inhibitors. With minimal human intervention, we combined AI-driven molecular design and retrosynthesis with IBM’s synthesis automation system RoboRXN…
Authors not listed
Automated synthesis and open-data practices are increasingly seen as key enablers of transparent, traceable, and reproducible science. By combining automation with structured, metadata-rich documentation, it becomes possible to systematically com- pare synthesis strategies and link outcomes to detailed parameters. In…