mlsanityData to 7 Oct 2026

AIDev: Studying AI Coding Agents on GitHub

arXiv 2602.09185 ↗First posted 9 Feb 2026cs.SE cs.AIcited by 15

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

AI coding agents are rapidly transforming software engineering by performing tasks such as feature development, debugging, and testing. Despite their growing impact, the research community lacks a comprehensive dataset capturing how these agents are used in real-world projects. To address this gap, we introduce AIDev, a large-scale dataset focused on agent-authored pull requests (Agentic-PRs) in real-world GitHub repositories. AIDev aggregates 932,791 Agentic-PRs produced by five agents: OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code. These PRs span 116,211 repositories and involve 72,189 developers. In addition, AIDev includes a curated subset of 33,596 Agentic-PRs from 2,807 repositories with over 100 stars, providing further information such as comments, reviews, commits, and related issues. This dataset offers a foundation for future research on AI adoption, developer productivity, and human-AI collaboration in the new era of software engineering. > AI Agent, Agentic AI, Coding Agent, Agentic Coding, Agentic Software Engineering, Agentic Engineering

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 27 of its 57 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

27 of 57 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Agentic Software Engineering: Foundational Pillars and a Research Roadmap7 Sep
  2. 2024HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale9 Sep
  3. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repair25 Mar

Other references · 24

  1. 2021Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributionscited by 417
  2. 2024AutoCodeRover: Autonomous Program Improvementcited by 272
  3. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 216
  4. 2023An Analysis of the Automatic Bug Fixing Performance of ChatGPTcited by 108
  5. 2022Productivity Assessment of Neural Code Completioncited by 97
  6. 2024Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Explorationcited by 58
  7. 2025Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Supportcited by 33
  8. 2024Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmapcited by 30
  9. 2024The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmerscited by 28
  10. 2024Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practicecited by 25
  11. 2024Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planningcited by 24
  12. 2024The Impact of Large Language Models on Open-source Innovation: Evidence from GitHub Copilotcited by 13
12 more
  1. 2022Automating Dependency Updates in Practice: An Exploratory Study on GitHub Dependabotcited by 12
  2. 2024A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actionscited by 12
  3. 2018How to Design a Program Repair Bot? Insights from the Repairnator Projectcited by 10
  4. 2020An Empirical Study of Bots in Software Development -- Characteristics and Challenges from a Practitioner's Perspectivecited by 8
  5. 2021Don't Disturb Me: Challenges of Interacting with SoftwareBots on Open Source Software Projectscited by 8
  6. 2025When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agentscited by 7
  7. 2021Bots Don't Mind Waiting, Do They? Comparing the Interaction With Automatically and Manually Created Pull Requestscited by 5
  8. 2023NoCodeGPT: A No-Code Interface for Building Web Apps with Language Modelscited by 4
  9. 2025Exploring the Challenges and Opportunities of AI-assisted Codebase Generationcited by 4
  10. 2025Emotional Strain and Frustration in LLM Interactions in Software Engineeringcited by 3
  11. 2022The Present and Future of Bots in Software Engineeringcited by 1
  12. 2025Beyond Code: The Multidimensional Impacts of Large Language Models in Software Developmentcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 15.

15 papers.

Sort:

By area:

  1. 2026Collaborator or Assistant? How AI Coding Agents Partition Work Across Pull Request Lifecyclescited by 2
  2. 2026Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Developmentcited by 2
  3. 2026All Smoke, No Alarm: Oracle Signals in Agent-Authored Test Codecited by 1
  4. 2026An Exploratory Study of Agent Plans for Agentic AI Coding Tools in Open-Source Softwarecited by 1
  5. 2026Where Accountability Lives: Mapping Human Responsibility to Workflow Artifacts in Agentic Software Developmentcited by 1
  6. 2026From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelinescited by 0
  7. 2026Quality and Security Signals in AI-Generated Python Refactoring Pull Requestscited by 0
  8. 2026Software Delegation Contracts: Measuring Reviewability in AI Coding-Agent Workcited by 0
  9. 2026Detecting AI Coding Agents in Open Source: A Validated Multi-Method Census of 180 Million Repositoriescited by 0
  10. 2026Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in AI-Native Softwarecited by 0
  11. 2026A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communitiescited by 0
  12. 2026From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentationcited by 0
3 more
  1. 2026On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplacescited by 0
  2. 2026Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requestscited by 0
  3. 2026Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebasecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
  2. 2026How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests
  3. 2026AI-to-AI Code Reviews of GitHub Pull Requests
  4. 2026AgenTag: Attribution of AI Coding Agents from Behavioral Fingerprints
  5. 2026Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
  6. 2026Understanding the Rejection of Fixes Generated by Agentic Pull Requests -- Insights from the AIDev Dataset
  7. 2026Fingerprinting AI Coding Agents on GitHub
  8. 2026Early Adoption of Agentic Coding Tools by GitHub Projects