@inproceedings{tang-etal-2026-self,
title = "Self-Revising Agents as Item Writers: Benchmarking Against Professional Item Writing",
author = "Tang, Steven and
Li, Zhen and
Patz, Richard",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting-Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference ({AIME}-Con): Works in Progress",
month = oct,
year = "2026",
address = "Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2026.aimecon-wip.47/",
pages = "369--376",
ISBN = "979-8-9983004-1-7",
abstract = "Expert reviewers rated 156 calculus items from a self-revising multi-agent framework (Claude Sonnet 4.6 or GPT-5.4, three prompt conditions) and 26 human-written items. AI items were formative-ready nearly as often as human items (78{--}80{\%} versus 88{\%}) but summative-ready less often (26{\%} and 10{\%} versus 58{\%}); a root-item reference mattered most."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2026-self">
<titleInfo>
<title>Self-Revising Agents as Item Writers: Benchmarking Against Professional Item Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Patz</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>Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Ormerod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magdalen</namePart>
<namePart type="family">Beiting-Parrish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>National Council on Measurement in Education (NCME)</publisher>
<place>
<placeTerm type="text">Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-9983004-1-7</identifier>
</relatedItem>
<abstract>Expert reviewers rated 156 calculus items from a self-revising multi-agent framework (Claude Sonnet 4.6 or GPT-5.4, three prompt conditions) and 26 human-written items. AI items were formative-ready nearly as often as human items (78–80% versus 88%) but summative-ready less often (26% and 10% versus 58%); a root-item reference mattered most.</abstract>
<identifier type="citekey">tang-etal-2026-self</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-wip.47/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>369</start>
<end>376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Revising Agents as Item Writers: Benchmarking Against Professional Item Writing
%A Tang, Steven
%A Li, Zhen
%A Patz, Richard
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-1-7
%F tang-etal-2026-self
%X Expert reviewers rated 156 calculus items from a self-revising multi-agent framework (Claude Sonnet 4.6 or GPT-5.4, three prompt conditions) and 26 human-written items. AI items were formative-ready nearly as often as human items (78–80% versus 88%) but summative-ready less often (26% and 10% versus 58%); a root-item reference mattered most.
%U https://aclanthology.org/2026.aimecon-wip.47/
%P 369-376
Markdown (Informal)
[Self-Revising Agents as Item Writers: Benchmarking Against Professional Item Writing](https://aclanthology.org/2026.aimecon-wip.47/) (Tang et al., AIME-Con 2026)
ACL