Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub

Documenti analoghi

• What Characteristics Make ChatGPT Effective for Software Issue Resolution? An Empirical Study of Task, Project, and Conversational Signals in GitHub Issues
  di: Ehsani, Ramtin, et al.
  Pubblicazione: (2025)
• Incivility in Open Source Projects: A Comprehensive Annotated Dataset of Locked GitHub Issue Threads
  di: Ehsani, Ramtin, et al.
  Pubblicazione: (2024)
• On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
  di: Watanabe, Miku, et al.
  Pubblicazione: (2025)
• Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution
  di: Ehsani, Ramtin, et al.
  Pubblicazione: (2025)
• Toxicity Ahead: Forecasting Conversational Derailment on GitHub
  di: Imran, Mia Mohammad, et al.
  Pubblicazione: (2025)