The rapid pace of large-scale software development places increasing demands on traditional testing methodologies, often leading to bottlenecks in efficiency, accuracy, and coverage. We propose a novel perspective on software testing by positing bug detection and coding with fewer bugs as two interconnected problems that share a common goal, which is reducing bugs with limited resources. We extend our previous work on AI-assisted programming, which supports code auto-completion and chatbot-powered Q&A, to the realm of software testing. We introduce Copilot for Testing, an automated testing system that synchronizes bug detection with codebase updates, leveraging context-based Retrieval Augmented Generation (RAG) to enhance the capabilities of large language models (LLMs). Our evaluation demonstrates a 31.2% improvement in bug detection accuracy, a 12.6% increase in critical test coverage, and a 10.5% higher user acceptance rate, highlighting the transformative potential of AI-driven technologies in modern software development practices.
Due to increased computing use, data centers consume and emit a lot of energy and carbon. These contributions are expected to rise as big data analytics, digitization, and large AI models grow and become major components of daily working routines. To reduce the environmental impact of software development, green (sustainable) coding and claims that AI models can improve energy efficiency have grown in popularity. Furthermore, in the automotive industry, where software increasingly governs vehicle performance, safety, and user experience, the principles of green coding and AI-driven efficiency could significantly contribute to reducing the sector's environmental footprint. We present an overview of green coding and metrics to measure AI model sustainability awareness. This study introduces LLM as a service and uses a generative commercial AI language model, GitHub Copilot, to auto-generate code. Using sustainability metrics to quantify these AI models' sustainability awareness, we define the code's embodied and operational carbon.
Language models (LMs) have become a staple of the code-writing toolbox. Their pre-training recipe has, however, remained stagnant over recent years, barring the occasional changes in data sourcing and filtering strategies. In particular, research exploring modifications to Code-LMs' pre-training objectives, geared towards improving data efficiency and better disentangling between syntax and semantics, has been noticeably sparse, especially compared with corresponding efforts in natural language LMs. In this work, we examine grounding on obfuscated code as a means of helping Code-LMs look beyond the surface-form syntax and enhance their pre-training sample efficiency. To this end, we compile ObscuraX, a dataset of approximately 55M source and obfuscated code pairs in seven languages. Subsequently, we pre-train ObscuraCoder models, ranging in size from 255M to 2.8B parameters, on a 272B-token corpus that includes ObscuraX and demonstrate that our obfuscation-based pre-training recipe leads to consistent improvements in Code-LMs' abilities compared to both vanilla autoregressive pre-training as well as existing de-obfuscation (DOBF) objectives. ObscuraCoder demonstrates sizeable gains across multiple tests of syntactic and semantic code understanding, along with improved capabilities in multilingual code completion, multilingual code commit summarization, and multi-purpose library-oriented code generation.
This paper explores the risk that a large language model (LLM) trained for code generation on data mined from software repositories will generate content that discloses sensitive information included in its training data. We decompose this risk, known in the literature as ``unintended memorization,'' into two components: unintentional disclosure (where an LLM presents secrets to users without the user seeking them out) and malicious disclosure (where an LLM presents secrets to an attacker equipped with partial knowledge of the training data). We observe that while existing work mostly anticipates malicious disclosure, unintentional disclosure is also a concern. We describe methods to assess unintentional and malicious disclosure risks side-by-side across different releases of training datasets and models. We demonstrate these methods through an independent assessment of the Open Language Model (OLMo) family of models and its Dolma training datasets. Our results show, first, that changes in data source and processing are associated with substantial changes in unintended memorization risk; second, that the same set of operational changes may increase one risk while mitigating another; and, third, that the risk of disclosing sensitive information varies not only by prompt strategies or test datasets but also by the types of sensitive information. These contributions rely on data mining to enable greater privacy and security testing required for the LLM training data supply chain.
Large Language Models (LLMs) have demonstrated exceptional performance in code generation tasks and have become indispensable programming assistants for developers. However, existing code generation benchmarks primarily assess the functional correctness of code generated by LLMs in single-turn interactions, offering limited insight into their capabilities to generate code that strictly follows users' instructions, especially in multi-turn interaction scenarios. In this paper, we introduce CodeIF-Bench, a benchmark for evaluating LLMs' instruction-following capabilities in interactive code generation. Specifically, CodeIF-Bench incorporates nine types of verifiable instructions aligned with the real-world software development requirements, which can be independently and objectively validated through specified test cases, facilitating the evaluation of instruction-following capability in multi-turn interactions. We evaluate nine prominent LLMs using CodeIF-Bench, and the experimental results reveal a significant disparity between their basic programming capability and instruction-following capability, particularly as task complexity, context length, and the number of dialogue rounds increase.
Modern code generation has made significant strides in functional correctness and execution efficiency. However, these systems often overlook a critical dimension in real-world software development: \textit{maintainability}. To handle dynamic requirements with minimal rework, we propose \textbf{MaintainCoder} as a pioneering solution. It integrates the Waterfall model, design patterns, and multi-agent collaboration to systematically enhance cohesion, reduce coupling, achieving clear responsibility boundaries and better maintainability. We also introduce \textbf{MaintainBench}, a benchmark comprising requirement changes and novel dynamic metrics on maintenance efforts. Experiments demonstrate that existing code generation methods struggle to meet maintainability standards when requirements evolve. In contrast, MaintainCoder improves dynamic maintainability metrics by more than 60\% with even higher correctness of initial codes. Furthermore, while static metrics fail to accurately reflect maintainability and even contradict each other, our proposed dynamic metrics exhibit high consistency. Our work not only provides the foundation for maintainable code generation, but also highlights the need for more realistic and comprehensive code generation research.
Unlike code generation, which involves creating code from scratch, code completion focuses on integrating new lines or blocks of code into an existing codebase. This process requires a deep understanding of the surrounding context, such as variable scope, object models, API calls, and database relations, to produce accurate results. These complex contextual dependencies make code completion a particularly challenging problem. Current models and approaches often fail to effectively incorporate such context, leading to inaccurate completions with low acceptance rates (around 30\%). For tasks like data transfer, which rely heavily on specific relationships and data structures, acceptance rates drop even further. This study introduces CCCI, a novel method for generating context-aware code completions specifically designed to address data transfer tasks. By integrating contextual information, such as database table relationships, object models, and library details into Large Language Models (LLMs), CCCI improves the accuracy of code completions. We evaluate CCCI using 289 Java snippets, extracted from over 819 operational scripts in an industrial setting. The results demonstrate that CCCI achieved a 49.1\% Build Pass rate and a 41.0\% CodeBLEU score, comparable to state-of-the-art methods that often struggle with complex task completion.
When using LLMs to address Non-Functional Requirements (NFRs), developers may behave differently (e.g., expressing the same NFR in different words). Robust LLMs should output consistent results across these variations; however, this aspect remains underexplored. We propose RobuNFR for evaluating the robustness of LLMs in NFR-aware code generation across four NFR dimensions: design, readability, reliability, and performance, using three methodologies: prompt variation, regression testing, and diverse workflows. Our experiments show that RobuNFR reveals robustness issues in the tested LLMs when considering NFRs in code generation. Specifically, under prompt variation, including NFRs leads to a decrease in Pass@1 by up to 39 percent and an increase in the standard deviation from 0.48 to 2.48 compared to the baseline without NFRs (i.e., Function-Only). While incorporating NFRs generally improves overall NFR metrics, it also results in higher prompt sensitivity. In regression settings, some LLMs exhibit differences across versions, with improvements in one aspect (e.g., reduced code smells) often accompanied by regressions in another (e.g., decreased correctness), revealing inconsistencies that challenge their robustness. When varying workflows, the tested LLMs show significantly different NFR-aware code generation capabilities between two workflows: (1) integrating NFRs and functional requirements into the initial prompt and (2) enhancing Function-Only-generated code with the same NFR.
Since the emergence of Large Language Models (LLMs) popularized by the release of GPT-3 and ChatGPT, LLMs have shown remarkable promise in programming-related tasks. While code generation using LLMs has become a popular field of research, code evaluation using LLMs remains under-explored. In this paper, we focus on LLM-based code evaluation and attempt to fill in the existing gaps. We propose multi-agentic novel approaches using \emph{question-specific rubrics} tailored to the problem statement, arguing that these perform better for logical assessment than the existing approaches that use \emph{question-agnostic rubrics}. To address the lack of suitable evaluation datasets, we introduce two datasets: a Data Structures and Algorithms dataset containing 150 student submissions from a popular Data Structures and Algorithms practice website, and an Object Oriented Programming dataset comprising 80 student submissions from undergraduate computer science courses. In addition to using standard metrics (Spearman Correlation, Cohen's Kappa), we additionally propose a new metric called as Leniency, which quantifies evaluation strictness relative to expert assessment. Our comprehensive analysis demonstrates that \emph{question-specific rubrics} significantly enhance logical assessment of code in educational settings, providing better feedback aligned with instructional goals beyond mere syntactic correctness.
LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases. LLMs' capabilities to autonomously find and fix runtime logical errors in complex data science code remain largely unexplored. To address this gap, we introduce DSDBench: the Data Science Debugging Benchmark, the first benchmark for systematic evaluation of LLMs on multi-hop error tracing and multi-bug detection in data science code debugging. DSDBench adapts datasets from existing data science task benchmarks, such as DABench and MatPlotBench, featuring realistic data science debugging tasks with automatically synthesized multi-hop, multi-bug code snippets. DSDBench includes 1,117 annotated samples with 741 cause-effect error pairs and runtime error messages. Evaluations of state-of-the-art LLMs on DSDBench show significant performance gaps, highlighting challenges in debugging logical runtime errors in data science code. DSDBench offers a crucial resource to evaluate and improve LLMs' debugging and reasoning capabilities, enabling more reliable AI-assisted data science in the future. DSDBench is publicly available at github.com/KevinCL16/DSDBench.
AI for software engineering has made remarkable progress recently, becoming a notable success within generative AI. Despite this, there are still many challenges that need to be addressed before automated software engineering reaches its full potential. It should be possible to reach high levels of automation where humans can focus on the critical decisions of what to build and how to balance difficult tradeoffs while most routine development effort is automated away. Reaching this level of automation will require substantial research and engineering efforts across academia and industry. In this paper, we aim to discuss progress towards this in a threefold manner. First, we provide a structured taxonomy of concrete tasks in AI for software engineering, emphasizing the many other tasks in software engineering beyond code generation and completion. Second, we outline several key bottlenecks that limit current approaches. Finally, we provide an opinionated list of promising research directions toward making progress on these bottlenecks, hoping to inspire future research in this rapidly maturing field.
Generating SystemVerilog Assertions (SVAs) from natural language specifications remains a major challenge in formal verification (FV) due to the inherent ambiguity and incompleteness of specifications. Existing LLM-based approaches, such as AssertLLM, focus on extracting information solely from specification documents, often failing to capture essential internal signal interactions and design details present in the RTL code, leading to incomplete or incorrect assertions. We propose a novel approach that constructs a Knowledge Graph (KG) from both specifications and RTL, using a hardware-specific schema with domain-specific entity and relation types. We create an initial KG from the specification and then systematically fuse it with information extracted from the RTL code, resulting in a unified, comprehensive KG. This combined representation enables a more thorough understanding of the design and allows for a multi-resolution context synthesis process which is designed to extract diverse verification contexts from the KG. Experiments on four designs demonstrate that our method significantly enhances SVA quality over prior methods. This structured representation not only improves FV but also paves the way for future research in tasks like code generation and design understanding.
Discrete-event simulation (DES) is widely used in healthcare Operations Research, but the models themselves are rarely shared. This limits their potential for reuse and long-term impact in the modelling and healthcare communities. This study explores the feasibility of using generative artificial intelligence (AI) to recreate published models using Free and Open Source Software (FOSS), based on the descriptions provided in an academic journal. Using a structured methodology, we successfully generated, tested and internally reproduced two DES models, including user interfaces. The reported results were replicated for one model, but not the other, likely due to missing information on distributions. These models are substantially more complex than AI-generated DES models published to date. Given the challenges we faced in prompt engineering, code generation, and model testing, we conclude that our iterative approach to model development, systematic comparison and testing, and the expertise of our team were necessary to the success of our recreated simulation models.
Large Language Models (LLMs) have demonstrated strong generalization capabilities across a wide range of natural language processing (NLP) tasks. However, they exhibit notable weaknesses in character-level string manipulation, struggling with fundamental operations such as character deletion, insertion, and substitution. These challenges stem primarily from tokenization constraints, despite the critical role of such operations in data preprocessing and code generation. Through systematic analysis, we derive two key insights: (1) LLMs face significant difficulties in leveraging intrinsic token knowledge for character-level reasoning, and (2) atomized word structures can substantially enhance LLMs' ability to process token-level structural information. Building on these insights, we propose Character-Level Manipulation via Divide and Conquer, a novel approach designed to bridge the gap between token-level processing and character-level manipulation. Our method decomposes complex operations into explicit character-level subtasks coupled with controlled token reconstruction phases, leading to significant improvements in accuracy. Without additional training, our method significantly improves accuracies on the $\texttt{Deletion}$, $\texttt{Insertion}$, and $\texttt{Substitution}$ tasks. To support further research, we open-source our implementation and benchmarks.
In this work, we investigate the merits of explicitly optimizing for inference time algorithmic performance during model training. We show how optimizing for inference time performance can improve overall model efficacy. We consider generic inference time objectives with $k$ samples, with a focus on pass@$k$ and majority voting as two main applications. With language model training on reasoning datasets, we showcase the performance trade-off enabled by training with such objectives. When training on code generation tasks, we show that the approach significantly improves pass@$k$ objectives compared to the baseline method.
Auto-vectorization is a fundamental optimization for modern compilers to exploit SIMD parallelism. However, state-of-the-art approaches still struggle to handle intricate code patterns, often requiring manual hints or domain-specific expertise. Large language models (LLMs), with their ability to capture intricate patterns, provide a promising solution, yet their effective application in compiler optimizations remains an open challenge due to issues such as hallucinations and a lack of domain-specific reasoning. In this paper, we present VecTrans, a novel framework that leverages LLMs to enhance compiler-based code vectorization. VecTrans first employs compiler analysis to identify potentially vectorizable code regions. It then utilizes an LLM to refactor these regions into patterns that are more amenable to the compilers auto-vectorization. To ensure semantic correctness, VecTrans further integrates a hybrid validation mechanism at the intermediate representation (IR) level. With the above efforts, VecTrans combines the adaptability of LLMs with the precision of compiler vectorization, thereby effectively opening up the vectorization opportunities. experimental results show that among all TSVC functions unvectorizable by GCC, ICC, Clang, and BiSheng Compiler, VecTrans achieves an geomean speedup of 1.77x and successfully vectorizes 24 of 51 test cases. This marks a significant advancement over state-of-the-art approaches while maintaining a cost efficiency of $0.012 per function optimization for LLM API usage.
The emergence of large language models and their applications as AI agents have significantly advanced state-of-the-art code generation benchmarks, transforming modern software engineering tasks. However, even with test-time computed reasoning models, these systems still struggle with complex software engineering challenges. This work introduces CURA, a code understanding and reasoning agent system enhanced with verbal process supervision (VPS), achieving a 3.65\% improvement over baseline models on challenging benchmarks like BigCodeBench. Furthermore, CURA, when paired with the o3-mini model and VPS techniques, attains state-of-the-art performance. This work represents a step forward in integrating reasoning-driven architectures with LLM-based code generation, enabling agentic reasoning for language models to solve complex software engineering tasks.
Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency. Many attempts have been released in the open source community to break the trade-off between performance and efficiency, such as the Qwen Coder series and the DeepSeek Coder series. This paper introduces yet another attempt in this area, namely Ling-Coder-Lite. We leverage the efficient Mixture-of-Experts (MoE) architecture along with a set of high-quality data curation methods (especially those based on program analytics) to build an efficient yet powerful code LLM. Ling-Coder-Lite exhibits on-par performance on 12 representative coding benchmarks compared to state-of-the-art models of similar size, such as Qwen2.5-Coder-7B and DeepSeek-Coder-V2-Lite, while offering competitive latency and throughput. In practice, we achieve a 50\% reduction in deployment resources compared to the similar-sized dense model without performance loss. To facilitate further research and development in this area, we open-source our models as well as a substantial portion of high-quality data for the annealing and post-training stages. The models and data can be accessed at~\url{https://huggingface.co/inclusionAI/Ling-Coder-lite}.
Modelica is a widely adopted language for simulating complex physical systems, yet effective model creation and optimization require substantial domain expertise. Although large language models (LLMs) have demonstrated promising capabilities in code generation, their application to modeling remains largely unexplored. To address this gap, we have developed benchmark datasets specifically designed to evaluate the performance of LLMs in generating Modelica component models and test cases. Our evaluation reveals substantial limitations in current LLMs, as the generated code often fails to simulate successfully. To overcome these challenges, we propose a specialized workflow that integrates supervised fine-tuning, graph retrieval-augmented generation, and feedback optimization to improve the accuracy and reliability of Modelica code generation. The evaluation results demonstrate significant performance gains: the maximum improvement in pass@1 reached 0.3349 for the component generation task and 0.2457 for the test case generation task. This research underscores the potential of LLMs to advance intelligent modeling tools and offers valuable insights for future developments in system modeling and engineering applications.
Research on using Large Language Models (LLMs) in system development is expanding, especially in automated code and test generation. While E2E testing is vital for ensuring application quality, most test generation research has focused on unit tests, with limited work on E2E test code. This study proposes a method for automatically generating E2E test code from product documentation such as manuals, FAQs, and tutorials using LLMs with tailored prompts. The two step process interprets documentation intent and produces executable test code. Experiments on a web app with six key features (e.g., authentication, profile, discussion) showed that tests generated from product documentation had high compilation success and functional coverage, outperforming those based on requirement specs and user stories. These findings highlight the potential of product documentation to improve E2E test quality and, by extension, software quality.