Automatic Categorization of GitHub Actions with Transformers and Few-shot Learning

• URL: http://arxiv.org/abs/2407.16946v1
• Date: Wed, 24 Jul 2024 02:27:36 GMT
• Title: Automatic Categorization of GitHub Actions with Transformers and Few-shot Learning
• Authors: Phuong T. Nguyen, Juri Di Rocco, Claudio Di Sipio, Mudita Shakya, Davide Di Ruscio, Massimiliano Di Penta,
• Abstract summary: GitHub Actions (GHA) have been conceived to provide developers with a practical tool to create and maintain a pipeline. To expose actions to search engines, GitHub allows developers to assign them to one or more categories manually. We propose Gavel, a practical solution to increasing the visibility of actions in GitHub.
• Score: 12.254055731378045
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In the GitHub ecosystem, workflows are used as an effective means to automate development tasks and to set up a Continuous Integration and Delivery (CI/CD pipeline). GitHub Actions (GHA) have been conceived to provide developers with a practical tool to create and maintain workflows, avoiding reinventing the wheel and cluttering the workflow with shell commands. Properly leveraging the power of GitHub Actions can facilitate the development processes, enhance collaboration, and significantly impact project outcomes. To expose actions to search engines, GitHub allows developers to assign them to one or more categories manually. These are used as an effective means to group actions sharing similar functionality. Nevertheless, while providing a practical way to execute workflows, many actions have unclear purposes, and sometimes they are not categorized. In this work, we bridge such a gap by conceptualizing Gavel, a practical solution to increasing the visibility of actions in GitHub. By leveraging the content of README.MD files for each action, we use Transformer--a deep learning algorithm--to assign suitable categories to the action. We conducted an empirical investigation and compared Gavel with a state-of-the-art baseline. The experimental results show that our proposed approach can assign categories to GitHub actions effectively, thus outperforming the state-of-the-art baseline.

Related papers

• WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models [105.46456444315693]
  We presentLLM, a data-centric framework to enhance the capability of large language models in workflow orchestration. It first constructs a large-scale fine-tuningBench with 106,763 samples, covering 1,503 APIs from 83 applications across 28 categories. LlamaLlama demonstrates a strong capacity to orchestrate complex APIs, while also achieving notable generalization performance.
  arXiv  Detail & Related papers  (2024-11-08T09:58:02Z)
• DynaSaur: Large Language Agents Beyond Predefined Actions [108.75187263724838]
  Existing LLM agent systems typically select actions from a fixed and predefined set at every step. We propose an LLM agent framework that enables the dynamic creation and composition of actions in an online manner. Our experiments on the GAIA benchmark demonstrate that this framework offers significantly greater flexibility and outperforms previous methods.
  arXiv  Detail & Related papers  (2024-11-04T02:08:59Z)
• The Hidden Costs of Automation: An Empirical Study on GitHub Actions Workflow Maintenance [45.53834452021771]
  GitHub Actions (GA) is an orchestration platform that streamlines the automatic execution of engineering tasks. Human intervention is necessary to correct defects, update dependencies, or existing workflow files.
  arXiv  Detail & Related papers  (2024-09-04T01:33:16Z)
• Detecting Continuous Integration Skip : A Reinforcement Learning-based Approach [0.4297070083645049]
  Continuous Integration (CI) practices facilitate the seamless integration of code changes by employing automated building and testing processes. Some frameworks, such as Travis CI and GitHub Actions have significantly contributed to simplifying and enhancing the CI process. Developers continue to encounter difficulties in accurately flagging commits as either suitable for CI execution or as candidates for skipping.
  arXiv  Detail & Related papers  (2024-05-15T18:48:57Z)
• On the effectiveness of Large Language Models for GitHub Workflows [9.82254417875841]
  Large Language Models (LLMs) have demonstrated their effectiveness in various software development tasks. We perform the first comprehensive study to understand the effectiveness of LLMs on five workflow-related tasks with different levels of prompts. Our evaluation of three state-of-art LLMs and their fine-tuned variants revealed various interesting findings on the current effectiveness and drawbacks of LLMs.
  arXiv  Detail & Related papers  (2024-03-19T05:14:12Z)
• Executable Code Actions Elicit Better LLM Agents [76.95566120678787]
  This work proposes to use Python code to consolidate Large Language Model (LLM) agents' actions into a unified action space (CodeAct) integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations through multi-turn interactions. The encouraging performance of CodeAct motivates us to build an open-source LLM agent that interacts with environments by executing interpretable code and collaborates with users using natural language.
  arXiv  Detail & Related papers  (2024-02-01T21:38:58Z)
• GitAgent: Facilitating Autonomous Agent with GitHub by Tool Extension [81.44231422624055]
  A growing area of research focuses on Large Language Models (LLMs) equipped with external tools capable of performing diverse tasks. In this paper, we introduce GitAgent, an agent capable of achieving the autonomous tool extension from GitHub.
  arXiv  Detail & Related papers  (2023-12-28T15:47:30Z)
• Automated DevOps Pipeline Generation for Code Repositories using Large Language Models [5.011328607647701]
  The research scrutinizes the proficiency of GPT 3.5 and GPT 4 in generating GitHub, while assessing the influence of various prompt elements in constructing the most efficient pipeline. Results indicate substantial advancements in GPT 4. The research introduces a GitHub App built on Probot, empowering users to automate workflow generation within GitHub ecosystem.
  arXiv  Detail & Related papers  (2023-12-20T17:47:52Z)
• A Preliminary Investigation of MLOps Practices in GitHub [10.190501703364234]
  Machine learning applications have led to an increasing interest in MLOps. We present an initial investigation of the MLOps practices implemented in a set of ML-enabled systems retrieved from GitHub.
  arXiv  Detail & Related papers  (2022-09-23T07:29:56Z)
• GitHub Actions: The Impact on the Pull Request Process [7.047566396769727]
  This study investigates how projects use GitHub Actions, what the developers discuss about them, and how project activity indicators change after their adoption. Our results indicate that 1,489 out of 5,000 most popular repositories (almost 30% of our sample) adopt GitHub Actions. Our findings also suggest that the adoption of GitHub Actions leads to more rejections of pull requests (PRs), more communication in accepted PRs and less communication in rejected PRs.
  arXiv  Detail & Related papers  (2022-06-28T16:24:17Z)
• Visual Transformer for Task-aware Active Learning [49.903358393660724]
  We present a novel pipeline for pool-based Active Learning. Our method exploits accessible unlabelled examples during training to estimate their co-relation with the labelled examples. Visual Transformer models non-local visual concept dependency between labelled and unlabelled examples.
  arXiv  Detail & Related papers  (2021-06-07T17:13:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.