arXiv AI
How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 27
How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests
arXiv:2607. 21832v1 Announce Type: cross Abstract: Recent advances in large language models and their rapid adoption across software engineering tasks have made Artificial Intelligence (AI) coding agents an integral component of modern software development workflows.
arXiv AI
Jul 22
Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality
arXiv:2607. 03691v2 Announce Type: replace-cross Abstract: Coding agents, autonomous systems that use large language models (LLMs) to resolve software engineering tasks, rely on agent harness: a middleware layer in between a developer and a large language model that orchestrates system prompts, tool execution, context management, and iterative reasoning loops.
arXiv AI
Jul 14
Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic Code
arXiv:2607. 09902v1 Announce Type: cross Abstract: Agentic coding tools are increasingly used to make autonomous repository-level changes to real-world projects.
arXiv AI
Jul 13
Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
arXiv:2607. 09510v1 Announce Type: cross Abstract: Large language model (LLM) coding agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a growing concern.
arXiv AI
Jul 14
How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study
arXiv:2607. 10856v1 Announce Type: cross Abstract: The rise of Software Engineering (SE) agents, i.
Hugging Face Trending Papers
Jul 30
Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments
Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification.