Alexey Svyatkovskiy

Zhiyu Li, Shuai Lu, Daya Guo et al. · microsoft-research

Code review is an essential part to software development lifecycle since it aims at guaranteeing the quality of codes. Modern code review activities necessitate developers viewing, understanding and even running the programs to assess logic, functionality, latency, style and other factors. It turns out that developers have to spend far too much time reviewing the code of their peers. Accordingly, it is in significant demand to automate the code review process. In this research, we focus on utilizing pre-training techniques for the tasks in the code review scenario. We collect a large-scale dataset of real-world code changes and code reviews from open-source projects in nine of the most popular programming languages. To better understand code diffs and reviews, we propose CodeReviewer, a pre-trained model that utilizes four pre-training tasks tailored specifically for the code review scenario. To evaluate our model, we focus on three key tasks related to code review activities, including code change quality estimation, review comment generation and code refinement. Furthermore, we establish a high-quality benchmark dataset based on our collected data for these three tasks and conduct comprehensive experiments on it. The experimental results demonstrate that our model outperforms the previous state-of-the-art pre-training approaches in all tasks. Further analysis show that our proposed pre-training tasks and the multilingual pre-training dataset benefit the model on the understanding of code changes and reviews.

Benjamin Steenhoek, Michele Tufano, Neel Sundaresan et al. · microsoft-research

Software testing is a crucial aspect of software development, and the creation of high-quality tests that adhere to best practices is essential for effective maintenance. Recently, Large Language Models (LLMs) have gained popularity for code generation, including the automated creation of test cases. However, these LLMs are often trained on vast amounts of publicly available code, which may include test cases that do not adhere to best practices and may even contain test smells (anti-patterns). To address this issue, we propose a novel technique called Reinforcement Learning from Static Quality Metrics (RLSQM). To begin, we analyze the anti-patterns generated by the LLM and show that LLMs can generate undesirable test smells. Thus, we train specific reward models for each static quality metric, then utilize Proximal Policy Optimization (PPO) to train models for optimizing a single quality metric at a time. Furthermore, we amalgamate these rewards into a unified reward model aimed at capturing different best practices and quality aspects of tests. By comparing RL-trained models with those trained using supervised learning, we provide insights into how reliably utilize RL to improve test generation quality and into the effects of various training strategies. Our experimental results demonstrate that the RL-optimized model consistently generated high-quality test cases compared to the base LLM, improving the model by up to 21%, and successfully generates nearly 100% syntactically correct code. RLSQM also outperformed GPT-4 on four out of seven metrics. This represents a significant step towards enhancing the overall efficiency and reliability of software testing through Reinforcement Learning and static quality metrics. Our data are available at https://figshare.com/s/ded476c8d4c221222849.

Shuaiwen Leon Song, Bonnie Kruft, Minjia Zhang et al. · microsoft-research

In the upcoming decade, deep learning may revolutionize the natural sciences, enhancing our capacity to model and predict natural occurrences. This could herald a new era of scientific exploration, bringing significant advancements across sectors from drug development to renewable energy. To answer this call, we present DeepSpeed4Science initiative (deepspeed4science.ai) which aims to build unique capabilities through AI system technology innovations to help domain experts to unlock today's biggest science mysteries. By leveraging DeepSpeed's current technology pillars (training, inference and compression) as base technology enablers, DeepSpeed4Science will create a new set of AI system technologies tailored for accelerating scientific discoveries by addressing their unique complexity beyond the common technical approaches used for accelerating generic large language models (LLMs). In this paper, we showcase the early progress we made with DeepSpeed4Science in addressing two of the critical system challenges in structural biology research.

Andrei Zlotchevski, Dawn Drain, Alexey Svyatkovskiy et al. · microsoft-research

Large Transformer models achieved the state-of-the-art status for Natural Language Understanding tasks and are increasingly becoming the baseline model architecture for modeling source code. Transformers are usually pre-trained on large unsupervised corpora, learning token representations and transformations relevant to modeling generally available text, and are then fine-tuned on a particular downstream task of interest. While fine-tuning is a tried-and-true method for adapting a model to a new domain -- for example, question-answering on a given topic -- generalization remains an on-going challenge. In this paper, we explore and evaluate transformer model fine-tuning for personalization. In the context of generating unit tests for Java methods, we evaluate learning to personalize to a specific software project using several personalization techniques. We consider three key approaches: (i) custom fine-tuning, which allows all the model parameters to be tuned; (ii) lightweight fine-tuning, which freezes most of the model's parameters, allowing tuning of the token embeddings and softmax layer only or the final layer alone; (iii) prefix tuning, which keeps model parameters frozen, but optimizes a small project-specific prefix vector. Each of these techniques offers a trade-off in total compute cost and predictive performance, which we evaluate by code and task-specific metrics, training time, and total computational operations. We compare these fine-tuning strategies for code generation and discuss the potential generalization and cost benefits of each in various deployment scenarios.

Shuai Lu, Nan Duan, Hojae Han et al.

Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development. Recent work has proved that statistical language modeling with transformers can greatly improve the performance in the code completion task via learning from large-scale source code datasets. However, current approaches focus only on code context within the file or project, i.e. internal context. Our distinction is utilizing "external" context, inspired by human behaviors of copying from the related code snippets when writing code. Specifically, we propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval. We adopt a stage-wise training approach that combines a source code retriever and an auto-regressive language model for programming language. We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.

Xiaoyu Liu, Jinu Jang, Neel Sundaresan et al. · cambridge, microsoft-research

In software development, it is common for programmers to copy-paste or port code snippets and then adapt them to their use case. This scenario motivates the code adaptation task -- a variant of program repair which aims to adapt variable identifiers in a pasted snippet of code to the surrounding, preexisting source code. However, no existing approach has been shown to effectively address this task. In this paper, we introduce AdaptivePaste, a learning-based approach to source code adaptation, based on transformers and a dedicated dataflow-aware deobfuscation pre-training task to learn meaningful representations of variable usage patterns. We evaluate AdaptivePaste on a dataset of code snippets in Python. Results suggest that our model can learn to adapt source code with 79.8% accuracy. To evaluate how valuable is AdaptivePaste in practice, we perform a user study with 10 Python developers on a hundred real-world copy-paste instances. The results show that AdaptivePaste reduces the dwell time to nearly half the time it takes for manual code adaptation, and helps to avoid bugs. In addition, we utilize the participant feedback to identify potential avenues for improvement of AdaptivePaste.

Benjamin Steenhoek, Michele Tufano, Neel Sundaresan et al. · microsoft-research

Software testing is a crucial but time-consuming aspect of software development, and recently, Large Language Models (LLMs) have gained popularity for automated test case generation. However, because LLMs are trained on vast amounts of open-source code, they often generate test cases that do not adhere to best practices and may even contain test smells (anti-patterns). To address this issue, we propose Reinforcement Learning from Static Quality Metrics (RLSQM), wherein we utilize Reinforcement Learning to generate high-quality unit tests based on static analysis-based quality metrics. First, we analyzed LLM-generated tests and show that LLMs frequently do generate undesirable test smells -- up to 37% of the time. Then, we implemented lightweight static analysis-based reward model and trained LLMs using this reward model to optimize for five code quality metrics. Our experimental results demonstrate that the RL-optimized Codex model consistently generated higher-quality test cases than the base LLM, improving quality metrics by up to 23%, and generated nearly 100% syntactically-correct code. RLSQM also outperformed GPT-4 on all code quality metrics, in spite of training a substantially cheaper Codex model. We provide insights into how reliably utilize RL to improve test generation quality and show that RLSQM is a significant step towards enhancing the overall efficiency and reliability of automated software testing. Our data are available at https://doi.org/10.6084/m9.figshare.25983166.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Michele Tufano, Dawn Drain, Alexey Svyatkovskiy et al.

Automated unit test case generation tools facilitate test-driven development and support developers by suggesting tests intended to identify flaws in their code. Existing approaches are usually guided by the test coverage criteria, generating synthetic test cases that are often difficult for developers to read or understand. In this paper we propose AthenaTest, an approach that aims to generate unit test cases by learning from real-world focal methods and developer-written testcases. We formulate unit test case generation as a sequence-to-sequence learning task, adopting a two-step training procedure consisting of denoising pretraining on a large unsupervised Java corpus, and supervised finetuning for a downstream translation task of generating unit tests. We investigate the impact of natural language and source code pretraining, as well as the focal context information surrounding the focal method. Both techniques provide improvements in terms of validation loss, with pretraining yielding 25% relative improvement and focal context providing additional 11.1% improvement. We also introduce Methods2Test, the largest publicly available supervised parallel corpus of unit test case methods and corresponding focal methods in Java, which comprises 780K test cases mined from 91K open-source repositories from GitHub. We evaluate AthenaTest on five defects4j projects, generating 25K passing test cases covering 43.7% of the focal methods with only 30 attempts. We execute the test cases, collect test coverage information, and compare them with test cases generated by EvoSuite and GPT-3, finding that our approach outperforms GPT-3 and has comparable coverage w.r.t. EvoSuite. Finally, we survey professional developers on their preference in terms of readability, understandability, and testing effectiveness of the generated tests, showing overwhelmingly preference towards AthenaTest.

Alexey Svyatkovskiy, Ying Zhao, Shengyu Fu et al.

In this paper, we propose a novel end-to-end approach for AI-assisted code completion called Pythia. It generates ranked lists of method and API recommendations which can be used by software developers at edit time. The system is currently deployed as part of Intellicode extension in Visual Studio Code IDE. Pythia exploits state-of-the-art large-scale deep learning models trained on code contexts extracted from abstract syntax trees. It is designed to work at a high throughput predicting the best matching code completions on the order of 100 $ms$. We describe the architecture of the system, perform comparisons to frequency-based approach and invocation-based Markov Chain language model, and discuss challenges serving Pythia models on lightweight client devices. The offline evaluation results obtained on 2700 Python open source software GitHub repositories show a top-5 accuracy of 92\%, surpassing the baseline models by 20\% averaged over classes, for both intra and cross-project settings.

Chenxiao Liu, Shuai Lu, Weizhu Chen et al.

Code execution is a fundamental aspect of programming language semantics that reflects the exact behavior of the code. However, most pre-trained models for code intelligence ignore the execution trace and only rely on source code and syntactic structures. In this paper, we investigate how well pre-trained models can understand and perform code execution. We develop a mutation-based data augmentation technique to create a large-scale and realistic Python dataset and task for code execution, which challenges existing models such as Codex. We then present CodeExecutor, a Transformer model that leverages code execution pre-training and curriculum learning to enhance its semantic comprehension. We evaluate CodeExecutor on code execution and show its promising performance and limitations. We also demonstrate its potential benefits for code intelligence tasks such as zero-shot code-to-code search and text-to-code generation. Our analysis provides insights into the learning and generalization abilities of pre-trained models for code execution.

Colin B. Clement, Shuai Lu, Xiaoyu Liu et al.

Statistical language modeling and translation with transformers have found many successful applications in program understanding and generation tasks, setting high benchmarks for tools in modern software development environments. The finite context window of these neural models means, however, that they will be unable to leverage the entire relevant context of large files and packages for any given task. While there are many efforts to extend the context window, we introduce an architecture-independent approach for leveraging the syntactic hierarchies of source code for incorporating entire file-level context into a fixed-length window. Using concrete syntax trees of each source file we extract syntactic hierarchies and integrate them into context window by selectively removing from view more specific, less relevant scopes for a given task. We evaluate this approach on code generation tasks and joint translation of natural language and source code in Python programming language, achieving a new state-of-the-art in code completion and summarization for Python in the CodeXGLUE benchmark. We also introduce new CodeXGLUE benchmarks for user-experience-motivated tasks: code completion with normalized literals, method body completion/code summarization conditioned on file-level context.

Alexey Svyatkovskiy, Sarah Fakhoury, Negar Ghorbani et al.

Collaborative software development is an integral part of the modern software development life cycle, essential to the success of large-scale software projects. When multiple developers make concurrent changes around the same lines of code, a merge conflict may occur. Such conflicts stall pull requests and continuous integration pipelines for hours to several days, seriously hurting developer productivity. To address this problem, we introduce MergeBERT, a novel neural program merge framework based on token-level three-way differencing and a transformer encoder model. By exploiting the restricted nature of merge conflict resolutions, we reformulate the task of generating the resolution sequence as a classification task over a set of primitive merge patterns extracted from real-world merge commit data. Our model achieves 63-68% accuracy for merge resolution synthesis, yielding nearly a 3x performance improvement over existing semi-structured, and 2x improvement over neural program merge tools. Finally, we demonstrate that MergeBERT is sufficiently flexible to work with source code files in Java, JavaScript, TypeScript, and C# programming languages. To measure the practical use of MergeBERT, we conduct a user study to evaluate MergeBERT suggestions with 25 developers from large OSS projects on 122 real-world conflicts they encountered. Results suggest that in practice, MergeBERT resolutions would be accepted at a higher rate than estimated by automatic metrics for precision and accuracy. Additionally, we use participant feedback to identify future avenues for improvement of MergeBERT.

Daya Guo, Alexey Svyatkovskiy, Jian Yin et al.

Code completion is usually cast as a language modelling problem, i.e., continuing an input in a left-to-right fashion. However, in practice, some parts of the completion (e.g., string literals) may be very hard to predict, whereas subsequent parts directly follow from the context. To handle this, we instead consider the scenario of generating code completions with "holes" inserted in places where a model is uncertain. We develop Grammformer, a Transformer-based model that guides code generation by the programming language grammar, and compare it to a variety of more standard sequence models. We train the models on code completion for C# and Python given partial code context. To evaluate models, we consider both ROUGE as well as a new metric RegexAcc that measures success of generating completions matching long outputs with as few holes as possible. In our experiments, Grammformer generates 10-50% more accurate completions compared to traditional generative models and 37-50% longer sketches compared to sketch-generating baselines trained with similar techniques.

Elizabeth Dinella, Todd Mytkowicz, Alexey Svyatkovskiy et al.

In collaborative software development, program merging is the mechanism to integrate changes from multiple programmers. Merge algorithms in modern version control systems report a conflict when changes interfere textually. Merge conflicts require manual intervention and frequently stall modern continuous integration pipelines. Prior work found that, although costly, a large majority of resolutions involve re-arranging text without writing any new code. Inspired by this observation we propose the first data-driven approach to resolve merge conflicts with a machine learning model. We realize our approach in a tool DeepMerge that uses a novel combination of (i) an edit-aware embedding of merge inputs and (ii) a variation of pointer networks, to construct resolutions from input segments. We also propose an algorithm to localize manual resolutions in a resolved file and employ it to curate a ground-truth dataset comprising 8,719 non-trivial resolutions in JavaScript programs. Our evaluation shows that, on a held out test set, DeepMerge can predict correct resolutions for 37% of non-trivial merges, compared to only 4% by a state-of-the-art semistructured merge technique. Furthermore, on the subset of merges with upto 3 lines (comprising 24% of the total dataset), DeepMerge can predict correct resolutions with 78% accuracy.

Dawn Drain, Chen Wu, Alexey Svyatkovskiy et al.

Detecting and fixing bugs are two of the most important yet frustrating parts of the software development cycle. Existing bug detection tools are based mainly on static analyzers, which rely on mathematical logic and symbolic reasoning about the program execution to detect common types of bugs. Fixing bugs is typically left out to the developer. In this work we introduce DeepDebug: a data-driven program repair approach which learns to detect and fix bugs in Java methods mined from real-world GitHub repositories. We frame bug-patching as a sequence-to-sequence learning task consisting of two steps: (i) denoising pretraining, and (ii) supervised finetuning on the target translation task. We show that pretraining on source code programs improves the number of patches found by 33% as compared to supervised training from scratch, while domain-adaptive pretraining from natural language to code further improves the accuracy by another 32%. We refine the standard accuracy evaluation metric into non-deletion and deletion-only fixes, and show that our best model generates 75% more non-deletion fixes than the previous state of the art. In contrast to prior work, we attain our best results when generating raw code, as opposed to working with abstracted code that tends to only benefit smaller capacity models. Finally, we observe a subtle improvement from adding syntax embeddings along with the standard positional embeddings, as well as with adding an auxiliary task to predict each token's syntactic class. Despite focusing on Java, our approach is language agnostic, requiring only a general-purpose parser such as tree-sitter.

Shuai Lu, Daya Guo, Shuo Ren et al.

Benchmark datasets have a significant impact on accelerating research in programming language tasks. In this paper, we introduce CodeXGLUE, a benchmark dataset to foster machine learning research for program understanding and generation. CodeXGLUE includes a collection of 10 tasks across 14 datasets and a platform for model evaluation and comparison. CodeXGLUE also features three baseline systems, including the BERT-style, GPT-style, and Encoder-Decoder models, to make it easy for researchers to use the platform. The availability of such data and baselines can help the development and validation of new methods that can be applied to various program understanding and generation problems.

Colin B. Clement, Dawn Drain, Jonathan Timcheck et al.

Simultaneously modeling source code and natural language has many exciting applications in automated software development and understanding. Pursuant to achieving such technology, we introduce PyMT5, the Python method text-to-text transfer transformer, which is trained to translate between all pairs of Python method feature combinations: a single model that can both predict whole methods from natural language documentation strings (docstrings) and summarize code into docstrings of any common style. We present an analysis and modeling effort of a large-scale parallel corpus of 26 million Python methods and 7.7 million method-docstring pairs, demonstrating that for docstring and method generation, PyMT5 outperforms similarly-sized auto-regressive language models (GPT2) which were English pre-trained or randomly initialized. On the CodeSearchNet test set, our best model predicts 92.1% syntactically correct method bodies, achieved a BLEU score of 8.59 for method generation and 16.3 for docstring generation (summarization), and achieved a ROUGE-L F-score of 24.8 for method generation and 36.7 for docstring generation.

Daya Guo, Shuo Ren, Shuai Lu et al.

Pre-trained models for programming language have achieved dramatic empirical improvements on a variety of code-related tasks such as code search, code completion, code summarization, etc. However, existing pre-trained models regard a code snippet as a sequence of tokens, while ignoring the inherent structure of code, which provides crucial code semantics and would enhance the code understanding process. We present GraphCodeBERT, a pre-trained model for programming language that considers the inherent structure of code. Instead of taking syntactic-level structure of code like abstract syntax tree (AST), we use data flow in the pre-training stage, which is a semantic-level structure of code that encodes the relation of "where-the-value-comes-from" between variables. Such a semantic-level structure is neat and does not bring an unnecessarily deep hierarchy of AST, the property of which makes the model more efficient. We develop GraphCodeBERT based on Transformer. In addition to using the task of masked language modeling, we introduce two structure-aware pre-training tasks. One is to predict code structure edges, and the other is to align representations between source code and code structure. We implement the model in an efficient way with a graph-guided masked attention function to incorporate the code structure. We evaluate our model on four tasks, including code search, clone detection, code translation, and code refinement. Results show that code structure and newly introduced pre-training tasks can improve GraphCodeBERT and achieves state-of-the-art performance on the four downstream tasks. We further show that the model prefers structure-level attentions over token-level attentions in the task of code search.

Michele Tufano, Dawn Drain, Alexey Svyatkovskiy et al.

Unit testing represents the foundational basis of the software testing pyramid, beneath integration and end-to-end testing. Automated software testing researchers have proposed a variety of techniques to assist developers in this time-consuming task. In this paper we present an approach to support developers in writing unit test cases by generating accurate and useful assert statements. Our approach is based on a state-of-the-art transformer model initially pretrained on an English textual corpus. This semantically rich model is then trained in a semi-supervised fashion on a large corpus of source code. Finally, we finetune this model on the task of generating assert statements for unit tests. The resulting model is able to generate accurate assert statements for a given method under test. In our empirical evaluation, the model was able to predict the exact assert statements written by developers in 62% of the cases in the first attempt. The results show 80% relative improvement for top-1 accuracy over the previous RNN-based approach in the literature. We also show the substantial impact of the pretraining process on the performances of our model, as well as comparing it with assert auto-completion task. Finally, we demonstrate how our approach can be used to augment EvoSuite test cases, with additional asserts leading to improved test coverage.

Alexey Svyatkovskiy, Shao Kun Deng, Shengyu Fu et al.

In software development through integrated development environments (IDEs), code completion is one of the most widely used features. Nevertheless, majority of integrated development environments only support completion of methods and APIs, or arguments. In this paper, we introduce IntelliCode Compose $-$ a general-purpose multilingual code completion tool which is capable of predicting sequences of code tokens of arbitrary types, generating up to entire lines of syntactically correct code. It leverages state-of-the-art generative transformer model trained on 1.2 billion lines of source code in Python, $C\#$, JavaScript and TypeScript programming languages. IntelliCode Compose is deployed as a cloud-based web service. It makes use of client-side tree-based caching, efficient parallel implementation of the beam search decoder, and compute graph optimizations to meet edit-time completion suggestion requirements in the Visual Studio Code IDE and Azure Notebook. Our best model yields an average edit similarity of $86.7\%$ and a perplexity of 1.82 for Python programming language.

Alexey Svyatkovskiy, Sebastian Lee, Anna Hadjitofi et al.

Code completion is one of the most widely used features of modern integrated development environments (IDEs). While deep learning has made significant progress in the statistical prediction of source code, state-of-the-art neural network models consume hundreds of megabytes of memory, bloating the development environment. We address this in two steps: first we present a modular neural framework for code completion. This allows us to explore the design space and evaluate different techniques. Second, within this framework we design a novel reranking neural completion model that combines static analysis with granular token encodings. The best neural reranking model consumes just 6 MB of RAM, - 19x less than previous models - computes a single completion in 8 ms, and achieves 90% accuracy in its top five suggestions.

Alexey Svyatkovskiy, Kosuke Imai, Mary Kroeger et al.

In this paper, we evaluate Apache Spark for a data-intensive machine learning problem. Our use case focuses on policy diffusion detection across the state legislatures in the United States over time. Previous work on policy diffusion has been unable to make an all-pairs comparison between bills due to computational intensity. As a substitute, scholars have studied single topic areas. We provide an implementation of this analysis workflow as a distributed text processing pipeline with Spark dataframes and Scala application programming interface. We discuss the challenges and strategies of unstructured data processing, data formats for storage and efficient access, and graph processing at scale.

Alexey Svyatkovskiy, Julian Kates-Harbeck, William Tang

In this paper, we evaluate training of deep recurrent neural networks with half-precision floats. We implement a distributed, data-parallel, synchronous training algorithm by integrating TensorFlow and CUDA-aware MPI to enable execution across multiple GPU nodes and making use of high-speed interconnects. We introduce a learning rate schedule facilitating neural network convergence at up to $O(100)$ workers. Strong scaling tests performed on clusters of NVIDIA Pascal P100 GPUs show linear runtime and logarithmic communication time scaling for both single and mixed precision training modes. Performance is evaluated on a scientific dataset taken from the Joint European Torus (JET) tokamak, containing multi-modal time series of sensory measurements leading up to deleterious events called plasma disruptions, and the benchmark Large Movie Review Dataset~\cite{imdb}. Half-precision significantly reduces memory and network bandwidth, allowing training of state-of-the-art models with over 70 million trainable parameters while achieving a comparable test set performance as single precision.