@inproceedings{zi-etal-2026-agentpack,
title = "{A}gent{P}ack: A Dataset of Code Changes, Co-Authored by Agents and Humans",
author = "Zi, Yangtian and
Wu, Zixuan and
Boruch-Gruszecki, Aleksander and
Bell, Jonathan and
Guha, Arjun",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.129/",
pages = "2631--2642",
ISBN = "979-8-89176-462-0",
abstract = "Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human intent in natural language, and patches to code describe the changes that implement that intent. However, much of the previously collected data is noisy: commit messages are terse, human-written commits commingle several unrelated edits, and many historical commits come from simple, rule-based bots.\par The recent adoption of software engineering agents changes this landscape. Code changes co-authored by humans and agents are often accompanied by substantially more explicit natural-language descriptions of intent and rationale. Moreover, changes in public repositories may have passed through human selection and review, and we treat this potential human filtering as an indirect signal of data quality.\par We present AgentPack, a corpus of 1.8M code edits co-authored by Claude Code, OpenAI Codex, and Cursor Agent across public GitHub projects up to early October 2025. We describe the identification and curation pipeline, quantify adoption trends of these agents, and analyze the structural properties of the edits. Finally, we show that models fine-tuned on AgentPack outperform models trained on prior human-only commit corpora, highlighting the potential of using public data from software engineering agents to train future code-editing models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zi-etal-2026-agentpack">
<titleInfo>
<title>AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yangtian</namePart>
<namePart type="family">Zi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixuan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksander</namePart>
<namePart type="family">Boruch-Gruszecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Bell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Guha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human intent in natural language, and patches to code describe the changes that implement that intent. However, much of the previously collected data is noisy: commit messages are terse, human-written commits commingle several unrelated edits, and many historical commits come from simple, rule-based bots.\par The recent adoption of software engineering agents changes this landscape. Code changes co-authored by humans and agents are often accompanied by substantially more explicit natural-language descriptions of intent and rationale. Moreover, changes in public repositories may have passed through human selection and review, and we treat this potential human filtering as an indirect signal of data quality.\par We present AgentPack, a corpus of 1.8M code edits co-authored by Claude Code, OpenAI Codex, and Cursor Agent across public GitHub projects up to early October 2025. We describe the identification and curation pipeline, quantify adoption trends of these agents, and analyze the structural properties of the edits. Finally, we show that models fine-tuned on AgentPack outperform models trained on prior human-only commit corpora, highlighting the potential of using public data from software engineering agents to train future code-editing models.</abstract>
<identifier type="citekey">zi-etal-2026-agentpack</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.129/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2631</start>
<end>2642</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
%A Zi, Yangtian
%A Wu, Zixuan
%A Boruch-Gruszecki, Aleksander
%A Bell, Jonathan
%A Guha, Arjun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zi-etal-2026-agentpack
%X Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human intent in natural language, and patches to code describe the changes that implement that intent. However, much of the previously collected data is noisy: commit messages are terse, human-written commits commingle several unrelated edits, and many historical commits come from simple, rule-based bots.\par The recent adoption of software engineering agents changes this landscape. Code changes co-authored by humans and agents are often accompanied by substantially more explicit natural-language descriptions of intent and rationale. Moreover, changes in public repositories may have passed through human selection and review, and we treat this potential human filtering as an indirect signal of data quality.\par We present AgentPack, a corpus of 1.8M code edits co-authored by Claude Code, OpenAI Codex, and Cursor Agent across public GitHub projects up to early October 2025. We describe the identification and curation pipeline, quantify adoption trends of these agents, and analyze the structural properties of the edits. Finally, we show that models fine-tuned on AgentPack outperform models trained on prior human-only commit corpora, highlighting the potential of using public data from software engineering agents to train future code-editing models.
%U https://aclanthology.org/2026.findings-emnlp.129/
%P 2631-2642
Markdown (Informal)
[AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans](https://aclanthology.org/2026.findings-emnlp.129/) (Zi et al., Findings 2026)
ACL