arXiv Computation and Language
AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Oct 26
What Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md
The study surveys popular, active GitHub repositories across thirteen languages, treating each repository’s AGENTS.md and CLAUDE.md files as instruction sets for coding agents. It finds that most repositories include such instructions, with CLAUDE.md often referencing AGENTS.md, and that these files contain a mix of project knowledge and workflow rules, including varying stances on AI attribution. The analysis reveals that more popular projects tend to have stricter pull‑request rules and AI contribution guidelines, and that LLM and agent projects are over‑represented among adopters.
arXiv AI
Sep 1
AgentLogs: A Dataset for Opening the Black Box of GitHub's Cloud Agent
arXiv:2608.29204v1 Announce Type: cross Abstract: Generative AI-based software engineering agents are becoming routine contributors to real-world software projects. On GitHub, developers can assign t...
arXiv AI
Jul 29
Learning from 53.6K Real-World Developer Edits of AI-Generated Code
arXiv:2607. 25130v1 Announce Type: cross Abstract: Imperfections in AI-generated code require that software developers modify the generated code manually, or by re-prompting an AI programming assistant.
arXiv AI
Oct 2
SWE-chat: Coding Agent Interactions From Real Users in the Wild
arXiv:2604.20779v2 Announce Type: replace Abstract: AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful...
arXiv AI
Jul 14
LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning
arXiv:2507. 16395v3 Announce Type: replace Abstract: Atomic commits, which address a single development concern, are a best practice in software development.
arXiv AI
Oct 31
How Do Developers Edit AI-Generated Code, and How Well Do LLMs Infer Their Edits? Insights from 53.6K Developer Edits
The paper introduces DECODE, a dataset of 53.6K real‑world in‑IDE edits of AI‑generated code from over 1,000 developers, and uses it to study when, why, and how developers modify such code. Findings show developers spend little effort editing and often abandon AI outputs, highlighting the need for LLMs to infer intent from edits. Experiments reveal that while frontier models can generate edits that align with developer intent, they tend to over‑edit and revert changes; fine‑tuning improves performance but does not fully close the gap.