paper-with-me

Papers

How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests

2026-01-24 · Daniel Ogenrwot, John Businge arxiv

AI coding agents are increasingly acting as autonomous contributors by generating and submitting pull requests (PRs). However, we lack empirical evidence on how these agent-generated PRs differ from human contributions, particularly in how they modify code and describe their changes. Understanding these differences is essential for assessing their reliability and impact on development workflows. Using the MSR 2026 Mining Challenge version of the AIDev dataset, we analyze 24,014 merged Agentic PRs (440,295 commits) and 5,081 merged Human PRs (23,242 commits). We examine additions, deletions, commits, and files touched, and evaluate the consistency between PR descriptions and their diffs using lexical and semantic similarity. Agentic PRs differ substantially from Human PRs in commit count (Cliff's $δ= 0.5429$) and show moderate differences in files touched and deleted lines. They also exhibit slightly higher description-to-diff similarity across all measures. These findings provide a large-scale empirical characterization of how AI coding agents contribute to open source development.

📄 PDF Abstract BibTeX arXiv:2601.17581

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Similarity

Similar Papers 제목 키워드 기반

MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification

2026-08-04 · Qiming Li, Shujie Hu, Haohan Liu, Xiaocheng Feng 외 arxiv

Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks predominantly focus on single-turn full-page generation from scratch, o…

SWE-Touch: Benchmarking Coding Agents When Users Touch the Code

2026-08-03 · Yuqiao Tan, Jinxiang Meng, Fangyu Lei, Minzheng Wang 외 hf

Real-world software development requires coding agents to operate in shared workspaces where users may inspect and modify code during an ongoing task, yet existing repository-level benchmarks typically evaluate agents wo…

Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation

2018-06-10 · NAACL 2018 6 · Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Stephan Vogel

We address the problem of simultaneous translation by modifying the Neural MT decoder to operate with dynamically built encoder and attention. We propose a tunable agent which decides the best segmentation strategy for a…

DecoderMachine TranslationTranslation

Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization

2024-04-02 · Yoichi Ishibashi, Yoshimasa Nishimura

Recent advancements in automatic code generation using large language model (LLM) agent have brought us closer to the future of automated software development. However, existing single-agent approaches face limitations i…

Code GenerationHumanEvalLanguage ModelingLanguage Modelling+1

Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study

2026-05-19 · Priyansh Trivedi, Olivier Schmitt arxiv

As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and styli…