build and validate prototypes

This work addresses the tight coupling between design intent and printer-specific representations in heterogeneous manufacturing, which hinders cross-platform reuse. The authors propose a novel compiler architecture that models fabrication-aware design as a staged, type-directed lowering process, decoupling source design, attribute translation, and backend compilation to enable manufacturing-agnostic expression. Introducing compiler paradigms to heterogeneous manufacturing for the first time, the approach unifies volumetric information—such as material composition, hardness, and color—through implicit geometry and typed spatial attribute fields, automatically generating voxel stacks, G-code, or slicer projects. Experiments demonstrate successful fabrication of complex objects embedding CT data, Shore hardness fields, and full-color fields on both material jetting and extrusion platforms, validating cross-process reusability. The accompanying Python toolkit is publicly released.

This work addresses the challenges faced by resource-constrained software startup teams with limited user experience (UX) expertise in efficiently creating and evaluating low-fidelity prototypes. To this end, we propose SoftBoard, a web-based multi-agent system that integrates large language model–driven intelligent agents into the prototyping workflow for the first time, enabling an end-to-end pipeline from requirement elicitation to automated generation of low-fidelity prototypes. The system incorporates an embedded evaluation mechanism based on usability heuristic rules and unifies prototype editing, team collaboration, and AI-assisted functionalities within a single platform, substantially reducing reliance on specialized UX knowledge. Preliminary feasibility studies demonstrate that SoftBoard effectively standardizes and streamlines the minimum viable product (MVP) development process.

To address the lack of systematic continuous verification and secure release mechanisms in open-source hardware design, this paper pioneers the systematic adaptation of software CI/CD paradigms to the hardware domain, proposing a general-purpose framework for automatic hardware specification mining and continuous deployment. Methodologically, it integrates HDL static analysis, machine learning–driven specification inference, formal verification, and cloud-native automated pipelines, implemented in the prototype system Myrtha. Key contributions include: (1) the first CI/CD architecture supporting continuous hardware specification generation, verification, and release; (2) a scalable, automated specification mining mechanism that overcomes traditional manual modeling bottlenecks; and (3) substantial improvements in quality assurance, experimental reproducibility, and cross-team collaboration efficiency for open-source hardware development.

In exploratory programming, fragmented feedback and inefficient comparison hinder iterative development; current informal practices—such as relying on memory, manual annotations, or screenshots—introduce errors and impede reproducibility. To address this, we propose Exploriants, a real-time, example-based programming extension. It introduces the novel “variant point” mechanism to automatically capture probe-style outputs during exploration and designs a domain-adaptive, parallel comparison view that transforms unstructured experimentation into a traceable, reproducible, structured iteration process. Our approach integrates example-driven programming, real-time probe-based output collection, and a configurable visualization interface for side-by-side comparison. We evaluate Exploriants across three domains—image processing, data processing, and game development—demonstrating statistically significant reductions in manual comparison errors, improved exploration efficiency, and enhanced accuracy in directionality assessment during iterative development.

To address the challenges of heterogeneity, fragmented resources, and inefficient collaboration in embedded-system virtual-prototype simulation tools, this paper proposes SUNRISE—a scalable infrastructure for distributed simulation. SUNRISE introduces the Simulation Adapter Abstraction Layer (SAAL), a novel abstraction enabling plug-and-play integration of seven major commercial and open-source simulators. It leverages lightweight containerization (Docker/Kubernetes) and a RESTful microservice architecture to dynamically orchestrate simulation tasks across decentralized computing resources. An open API gateway is designed to facilitate cross-organizational collaboration. Experimental evaluation demonstrates that SUNRISE reduces simulation-task deployment latency by 62%, improves cross-organizational collaboration efficiency by 3×, and achieves a 99.8% API call success rate.

This work proposes a personalized prototyping platform for circuit development to address the limitations of traditional tutorial-based approaches, which rely on rigid, fixed-step instructions that fail to accommodate makers’ individualized building and debugging practices. Central to the platform is a circuit-aware enhanced breadboard integrated with hardware-in-the-loop reconfiguration, context-aware guidance algorithms, and in-situ interactive testing techniques. This integration enables, for the first time, nonlinear, real-time, hardware-context-driven guidance and circuit validation. A user study (N=12) demonstrates that the system effectively aligns with users’ unique construction and troubleshooting behaviors, significantly improving both prototyping efficiency and user experience.

This work addresses the frequent failures in current autonomous AI coding systems—stemming from uncontrolled engineering processes in software and hardware development, particularly in configuration, dependency management, permission handling, and hardware verification. To tackle these challenges, the authors propose the Agentic Agile-V framework, which anchors the development lifecycle in the Agile V-model and introduces a task-level SCOPE-V loop (Specify, Constrain, Orchestrate, Prove, Evolve, Verify) to translate conversational intent into structured engineering artifacts and verifiable evidence. Key contributions include an agent-oriented minimal input artifact taxonomy, a gated mechanism for converting dialogue into formal contracts, a risk-adaptive workflow, and an evidence-bundle-based artifact acceptance model. Empirical results demonstrate that this approach significantly enhances the reliability and controllability of AI-assisted development in complex projects, yielding more stable delivery outcomes and higher verification pass rates.

This study addresses the persistent challenges of inefficiency and inconsistent design fidelity that developers encounter when translating high-fidelity mockups into production-grade user interfaces. Through controlled experiments conducted across Angular, iOS, and Android platforms in an industrial setting, the work presents the first empirical evaluation of an AI-assisted development tool integrated with a design system. The findings demonstrate that this approach substantially enhances both development efficiency and design consistency: delivery time was reduced by 46.7%–69.4%, task completion rates improved, performance variability decreased, and workflow friction was markedly alleviated. These results validate the synergistic value of design-system-aware AI tools in enabling automation and standardization across multi-platform front-end development workflows.

This work addresses the challenge of constructing effective test oracles for Functional Mock-up Unit (FMU) simulation models, which lack explicit expected outputs and thus hinder the application of traditional testing methods. Furthermore, existing approaches to extracting metamorphic relations rely heavily on manual effort, resulting in low efficiency and susceptibility to human error. To overcome these limitations, the paper proposes a novel large language model (LLM)-based multi-agent workflow that, for the first time, integrates LLMs with multi-agent collaboration to automatically derive requirements from functional and interface specifications and generate structured Given-When-Then metamorphic relations. These relations drive the automated generation of metamorphic test cases and consistency validation for FMUs. Experimental evaluation on an oil cooling system FMU demonstrates that the approach significantly reduces manual intervention while enhancing the systematicity and efficiency of dynamic simulation model verification.

This work addresses the absence of standardized benchmarks for evaluating large language models (LLMs) and vision-language models (VLMs) in multi-stage optimization and collaboration with electronic design automation (EDA) tools within VLSI physical design. It introduces the first comprehensive evaluation framework tailored to this domain, comprising five dimensions—knowledge comprehension, report analysis, root-cause diagnosis, script generation, and end-to-end implementation—with 353 industry-validated questions verified by domain experts. The benchmark integrates real-world EDA environments, such as Cadence Innovus, enabling closed-loop assessment. Experimental results reveal that while current models perform reasonably on conceptual tasks, they exhibit significant deficiencies in tool interaction—evidenced by a mere 42.2% accuracy in Innovus script generation—and long-horizon reasoning. Incorporating human-in-the-loop workflows substantially enhances end-to-end design performance.