共找到 20 条结果
Software engineering is experiencing its most significant transformation since the emergence of high-level programming languages. As large language models (LLMs) increasingly enable sustained, multi-step, tool-mediated execution, engineering value is shifting from writing deterministic code to supervising probabilistic and autonomous behavior. This paper argues that AI-Native Software Engineering is a paradigm shift rather than a mere tooling advance, creating a new professional archetype: the Agentic Engineer, whose primary artifact is the agentic system rather than the program. We characterize this transition through three changes: (i) the unit of work shifts from functions to supervised agent workflows, (ii) correctness shifts from binary assertions to statistical evaluation under uncertainty, and (iii) accountability shifts from code authorship to outcome ownership. Drawing on post-2022 research, we compare traditional and agentic engineering roles and define core mechanisms of autonomous agents, including reasoning-acting loops, context engineering, tool use, memory, behavioral drift, and compositional error. We place human-AI collaboration within socio-technical frameworks an
With the rapid rise of AI coding agents, the fundamental premise of what it means to be a software engineer is in question. In this vision paper, we examine what it means for an AI agent to be considered a software engineer and then critically think about what makes such an agent trustworthy. Grounded in established definitions of SE (SE) and informed by recent research on agentic AI systems, we conceptualise AI software engineers as participants in human-AI SE teams composed of human software engineers and AI agents, and we distinguish trustworthiness as a key property of these systems and actors rather than a subjective human attitude. Extending on historical perspectives and emerging visions, we identify key dimensions that contribute to the trustworthiness of AI software engineers, spanning technical quality, transparency and accountability, epistemic humility, and societal and ethical alignment. Beyond defining these dimensions, we address a critical but underexplored challenge: how trustworthiness can be operationalised in practice. We therefore introduce the notion of evidence-centric inspection, arguing that developers should evaluate selective signals and justifications of
In modern engineering practice, human engineers collaborate in specialized teams to design complex products, with each expert completing their respective tasks while communicating and exchanging results and data with one another. While this division of expertise is essential for managing multidisciplinary complexity, it demands substantial development time and cost. Recently, we introduced OpenFOAMGPT (1.0, 2.0), which functions as an autonomous AI engineer for computational fluid dynamics, and turbulence.ai, which can conduct end-to-end research in fluid mechanics draft publications and PhD theses. Building upon these foundations, we present Engineering.ai, a platform for teams of AI engineers in computational design. The framework employs a hierarchical multi-agent architecture where a Chief Engineer coordinates specialized agents consisting of Aerodynamics, Structural, Acoustic, and Optimization Engineers, each powered by LLM with domain-specific knowledge. Agent-agent collaboration is achieved through file-mediated communication for data provenance and reproducibility, while a comprehensive memory system maintains project context, execution history, and retrieval-augmented doma
The rise of large language models (LLMs) has created a new job role: the Prompt Engineer. Despite growing interest in this position, we still do not fully understand what skills this new job role requires or how common these jobs are. In this paper, we present a data-driven analysis of global prompt engineering job trends on LinkedIn. We take a snapshot of the evolving AI workforce by analyzing 20,662 job postings on LinkedIn, including 72 prompt engineer positions, to learn more about this emerging role. We find that prompt engineering is still rare (less than 0.5% of sampled job postings) but has a unique skill profile. Prompt engineers need AI knowledge (22.8%), prompt design skills (18.7%), good communication (21.9%), and creative problem-solving (15.8%) skills. These requirements significantly differ from those of established roles, such as data scientists and machine learning engineers. Our findings help job seekers, employers, and educational institutions in better understanding the emerging field of prompt engineering.
Engineering a sustainable world requires to consider various systems that interact with each other. These systems include ecological systems, economical systems, social systems and tech-nical systems. They are loosely coupled, geographically distributed, evolve permanently and generate emergent behavior. As these are characteristics of systems of systems (SoS), we discuss the engi-neering of a sustainable world from a SoS engineering perspective. We studied SoS engineering in context of a research project, which aims at political recommendations and a research roadmap for engineering dynamic SoS. The project included an exhaustive literature review, interviews and work-shops with representatives from industry and academia from different application domains. Based on these results and observations, we will discuss how suitable the current state-of-the-art in SoS engi-neering is in order to engineer sustainability. Sustainability was a major driver for SoS engineering in all domains, but we argue that the current scope of SoS engineering is too limited in order to engineer sustainability. Further, we argue that mastering dynamics in this larger scope is essential to engineer sustaina
The growth of Large Language Model (LLM) technology has raised expectations for automated coding. However, software engineering is more than coding and is concerned with activities including maintenance and evolution of a project. In this context, the concept of LLM agents has gained traction, which utilize LLMs as reasoning engines to invoke external tools autonomously. But is an LLM agent the same as an AI software engineer? In this paper, we seek to understand this question by developing a Unified Software Engineering agent or USEagent. Unlike existing work which builds specialized agents for specific software tasks such as testing, debugging, and repair, our goal is to build a unified agent which can orchestrate and handle multiple capabilities. This gives the agent the promise of handling complex scenarios in software development such as fixing an incomplete patch, adding new features, or taking over code written by others. We envision USEagent as the first draft of a future AI Software Engineer which can be a team member in future software development teams involving both AI and humans. To evaluate the efficacy of USEagent, we build a Unified Software Engineering bench (USEbe
This study investigates a new approach for scheduling freight rail engineers based on call windows under the Hours of Service (HOS) regulations. Unlike planned trip assignments, call windows specify a time interval during which an engineer may be required to start work, thus providing greater flexibility to handle uncertain trip demand while offering drivers more predictable off-duty periods. Currently in the U.S., all major freight operators require drivers to be available 24/7 outside of mandatory rest periods, raising concerns over workforce fatigue and safety. We formalize the call-window scheduling problem and propose two solution approaches: a Set-covering-type optimization model and a Direct Algorithm. Both aim to maximize demand coverage while minimizing the number of engineers subject to HOS feasibility. Computational experiments for 2-city and 3-city instances with varying call window lengths, maximum delay allowances, and whether to allow deadhead trips show that the Set-covering-type model yields higher demand undercoverage (94.89% and 91.09% for 2-city and 3-city instances, respectively) than the Direct Algorithm (93.96% and 71.83%). It also offers greater rest opportu
The engineering design process often demands expertise from multiple domains, leading to complex collaborations and iterative refinements. Traditional methods can be resource-intensive and prone to inefficiencies. To address this, we formalize the engineering design process through a multi-agent AI framework that integrates structured design and review loops. The framework introduces specialized knowledge-driven agents that collaborate to generate and refine design candidates. As an exemplar, we demonstrate its application to the aerodynamic optimization of 4-digit NACA airfoils. The framework consists of three key AI agents: a Graph Ontologist, a Design Engineer, and a Systems Engineer. The Graph Ontologist employs a Large Language Model (LLM) to construct two domain-specific knowledge graphs from airfoil design literature. The Systems Engineer, informed by a human manager, formulates technical requirements that guide design generation and evaluation. The Design Engineer leverages the design knowledge graph and computational tools to propose candidate airfoils meeting these requirements. The Systems Engineer reviews and provides feedback both qualitative and quantitative using its
Digital twins promise a better understanding and use of complex systems. To this end, they represent these systems at their runtime and may interact with them to control their processes. Software engineering is a wicked challenge in which stakeholders from many domains collaborate to produce software artifacts together. In the presence of skilled software engineer shortage, our vision is to leverage DTs as means for better rep- resenting, understanding, and optimizing software engineering processes to (i) enable software experts making the best use of their time and (ii) support domain experts in producing high-quality software. This paper outlines why this would be beneficial, what such a digital twin could look like, and what is missing for realizing and deploying software engineering digital twins.
This paper explores the intricate challenge of understanding and measuring software engineer behavior. More specifically, we revolve around a central question: How can we enhance our understanding of software engineer behavior? Grounded in the nuanced complexities addressed within Behavioral Software Engineering (BSE), we advocate for holistic methods that integrate quantitative measures, such as psychometric instruments, and qualitative data from diverse sources. Furthermore, we delve into the relevance of this challenge within national and international contexts, highlighting the increasing interest in understanding software engineer behavior. Real-world initiatives and academic endeavors are also examined to underscore the potential for advancing this research agenda and, consequently, refining software engineering practices based on behavioral aspects. Lastly, this paper addresses different ways to evaluate the progress of this challenge by leveraging methodological skills derived from behavioral sciences, ultimately contributing to a deeper understanding of software engineer behavior and software engineering practices.
Software Quality Assurance (SQA) Engineers are responsible for assessing a product during every phase of the software development process to ensure that the outcomes of each phase and the final product possess the desired qualities. In general, a great SQA engineer needs to have a different set of abilities from development engineers to effectively oversee the entire product development process from beginning to end. Recent empirical studies identified important attributes of software engineers and managers, but the quality assurance role is overlooked. As software quality aspects have become more of a priority in the life cycle of software development, employers seek professionals that best suit the company's objectives and new graduates desire to make a valuable contribution through their job as an SQA engineer, but what makes them great? We addressed this knowledge gap by conducting 25 semi-structured interviews and 363 survey respondents with software quality assurance engineers from different companies around the world. We use the data collected from these activities to derive a comprehensive set of attributes that are considered important. As a result of the interviews, twent
Systems engineering processes coordinate the effort of different individuals to generate a product satisfying certain requirements. As the involved engineers are self-interested agents, the goals at different levels of the systems engineering hierarchy may deviate from the system-level goals which may cause budget and schedule overruns. Therefore, there is a need of a systems engineering theory that accounts for the human behavior in systems design. To this end, the objective of this paper is to develop and analyze a principal-agent model of a one-shot (single iteration), shallow (one level of hierarchy) systems engineering process. We assume that the systems engineer maximizes the expected utility of the system, while the subsystem engineers seek to maximize their expected utilities. Furthermore, the systems engineer is unable to monitor the effort of the subsystem engineer and may not have a complete information about their types or the complexity of the design task. However, the systems engineer can incentivize the subsystem engineers by proposing specific contracts. To obtain an optimal incentive, we pose and solve numerically a bi-level optimization problem. Through extensive
Recently, Devin has made a significant buzz in the Artificial Intelligence (AI) community as the world's first fully autonomous AI software engineer, capable of independently developing software code. Devin uses the concept of agentic workflow in Generative AI (GenAI), which empowers AI agents to engage in a more dynamic, iterative, and self-reflective process. In this paper, we present a similar fully autonomous AI formal verification engineer, Saarthi, capable of verifying a given RTL design end-to-end using an agentic workflow. With Saarthi, verification engineers can focus on more complex problems, and verification teams can strive for more ambitious goals. The domain-agnostic implementation of Saarthi makes it scalable for use across various domains such as RTL design, UVM-based verification, and others.
We develop a systematic perturbative framework to engineer an arbitrary target Hamiltonian in the Floquet phase space of a periodically driven oscillator based on Floquet-Magnus expansion. The high-order errors in the engineered Floquet Hamiltonian are mitigated by adding high-order driving potentials perturbatively. We introduce a transformation method that allows us to obtain an analytical expression of the leading-order correction drive for engineering a target Hamiltonian with discrete rotational and chiral symmetries in phase space. We also provide a numerically efficient procedure to calculate high-order correction drives and apply it to engineer the target Hamiltonian with degenerate eigenstates of multi-component cat states that are important for fault-tolerant hardware-efficiency bosonic quantum computation.
We present a principal-agent model of a one-shot, shallow, systems engineering process. The process is one-shot in the sense that decisions are made during one time step and that they are final. The term shallow refers to a one-layer hierarchy of the process. Specifically, we assume that the systems engineer has already decomposed the problem in subsystems, and that each subsystem is assigned to a different subsystem engineer. Each subsystem engineer works independently to maximize their own expected payoff. The goal of the systems engineer is to maximize the system-level payoff by incentivizing the subsystem engineers. We restrict our attention to requirement-based system-level payoffs, i.e., the systems engineer makes a profit only if all the design requirements are met. We illustrate the model using the design of an Earth-orbiting satellite system where the systems engineer determines the optimum incentive structures and requirements for two subsystems: the propulsion subsystem and the power subsystem. The model enables the analysis of a systems engineer's decisions about optimal passed-down requirements and incentives for sub-system engineers under different levels of task diff
Reverse engineering has been a standard practice in the hardware community for some time. It has only been within the last ten years that reverse engineering, or "program comprehension", has grown into the current sub-discipline of software engineering. Traditional software engineering is primarily focused on the development and design of new software. However, most programmers work on software that other people have designed and developed. Up to 50% of a software maintainers time can be spent determining the intent of source code. The growing demand to reevaluate and reimplement legacy software systems, brought on by the proliferation of clientserver and World Wide Web technologies, has underscored the need for reverse engineering tools and techniques. This paper introduces the terminology of reverse engineering and gives some of the obstacles that make reverse engineering difficult. Although reverse engineering remains heavily dependent on the human component, a number of automated tools are presented that aid the reverse engineer.
Evidence-based practice (EBP) in software engineering aims to improve decision-making in software development by complementing practitioners' professional judgment with high-quality evidence from research. We believe the use of EBP techniques may be helpful for research software engineers (RSEs) in their work to bring software engineering best practices to scientific software development. In this study, we present an experience report on the use of a particular EBP technique, rapid reviews, within an RSE team at Sandia National Laboratories, and present practical recommendations for how to address barriers to EBP adoption within the RSE community.
Implementing the time evolution under a desired target Hamiltonian is critical for various applications in quantum science. Due to the exponential increase in the number of parameters with system size and experimental imperfections, this task can be challenging in quantum many-body settings. We introduce an efficient and robust scheme to engineer arbitrary local many-body Hamiltonians. To this end, our scheme applies single-qubit $π$ or $π/2$ pulses to an always-on system Hamiltonian, which we assume to be native to a given platform. These sequences are constructed by efficiently solving a linear program (LP) which minimizes the total evolution time. In this way, we can engineer target Hamiltonians that are only limited by the locality of the interactions in the system Hamiltonian. Based on average Hamiltonian theory and using robust composite pulses, we make our schemes robust against errors, including finite pulse time errors and various control errors. To demonstrate the performance of our scheme, we provide numerical simulations. In particular, we solve the Hamiltonian engineering problem on a laptop for arbitrary two-local Hamiltonians on a 2D square lattice with $196$ qubits
Advancements in chip design and manufacturing have enabled the processing of complex tasks such as deep learning and natural language processing, paving the way for the development of artificial general intelligence (AGI). AI, on the other hand, can be leveraged to innovate and streamline semiconductor technology from planning and implementation to manufacturing. In this paper, we present \textit{Intelligent OPC Engineer Assistant}, an AI/LLM-powered methodology designed to solve the core manufacturing-aware optimization problem known as optical proximity correction (OPC). The methodology involves a reinforcement learning-based OPC recipe search and a customized multi-modal agent system for recipe summarization. Experiments demonstrate that our methodology can efficiently build OPC recipes on various chip designs with specially handled design topologies, a task that typically requires the full-time effort of OPC engineers with years of experience.
The capacity to custom tailor the properties of quantum matter and materials is a central requirement for enlarging their range of possible functionalities. A particularly promising route is the use of driving protocols to engineer specific desired properties with a high degree of control and flexibility. Here, we present such a program for the tunable generation of sequences of symmetries on controllable timescales. Concretely, our general driving protocol for many-body systems generates a sequence of prethermal regimes, each exhibiting a lower symmetry than the preceding one. We provide an explicit construction of effective Hamiltonians exhibiting these symmetries, which imprints emergent quasiconservation laws hierarchically, enabling us to engineer the respective symmetries and concomitant orders in nonequilibrium matter. We provide explicit examples, including spatiotemporal and topological phenomena, as well as a spin chain realizing the symmetry ladder $\text{SU(2)}{\rightarrow}\text{U(1)} {\rightarrow} \mathbb{Z}_2{\rightarrow} E$. Our results have direct applications in experiments with quantum simulators.