@inproceedings{li-etal-2026-flexscieval,
title = "{F}lex{S}ci{E}val: Structure-Grounded Multi-agent Evaluation for Flexible Electronics Research",
author = "Li, Ke and
Yang, Xinyi and
Zhan, Runzhe and
Hu, Qianyong and
Wong, Derek F. and
Li, Qingsong and
Liu, Zhiyuan",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.87/",
pages = "1243--1262",
ISBN = "979-8-89176-485-9",
abstract = "Evaluating research in flexible electronics requires weighing evidence across multiple technical and manufacturing dimensions. However, current LLM-based approaches largely rely on unstructured text and generic evaluation criteria, limiting their ability to assess scientific work at the device level. We present FlexSciEval, a multi-agent framework that first turns each paper or research plan into an auditable structured record, then uses dimension-specific agents to score academic impact, fabrication realizability, and novelty. We also construct a 60-paper expert-annotated benchmark for validation and scale the framework to 4,158 papers. FlexSciEval reduces overall mean absolute error by 10.4{\%} compared with direct LLM evaluation on the benchmark annotated by experts, although gains vary by model and dimension. These results indicate that grounding LLM evaluation in structured and dimension-specific evidence improves the reliability of automated scientific assessment in the field of flexible electronics, providing a practical basis for more reliable agent-based evaluation in experimental device research in the future."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-flexscieval">
<titleInfo>
<title>FlexSciEval: Structure-Grounded Multi-agent Evaluation for Flexible Electronics Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runzhe</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianyong</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingsong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</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">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>Evaluating research in flexible electronics requires weighing evidence across multiple technical and manufacturing dimensions. However, current LLM-based approaches largely rely on unstructured text and generic evaluation criteria, limiting their ability to assess scientific work at the device level. We present FlexSciEval, a multi-agent framework that first turns each paper or research plan into an auditable structured record, then uses dimension-specific agents to score academic impact, fabrication realizability, and novelty. We also construct a 60-paper expert-annotated benchmark for validation and scale the framework to 4,158 papers. FlexSciEval reduces overall mean absolute error by 10.4% compared with direct LLM evaluation on the benchmark annotated by experts, although gains vary by model and dimension. These results indicate that grounding LLM evaluation in structured and dimension-specific evidence improves the reliability of automated scientific assessment in the field of flexible electronics, providing a practical basis for more reliable agent-based evaluation in experimental device research in the future.</abstract>
<identifier type="citekey">li-etal-2026-flexscieval</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.87/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1243</start>
<end>1262</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FlexSciEval: Structure-Grounded Multi-agent Evaluation for Flexible Electronics Research
%A Li, Ke
%A Yang, Xinyi
%A Zhan, Runzhe
%A Hu, Qianyong
%A Wong, Derek F.
%A Li, Qingsong
%A Liu, Zhiyuan
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F li-etal-2026-flexscieval
%X Evaluating research in flexible electronics requires weighing evidence across multiple technical and manufacturing dimensions. However, current LLM-based approaches largely rely on unstructured text and generic evaluation criteria, limiting their ability to assess scientific work at the device level. We present FlexSciEval, a multi-agent framework that first turns each paper or research plan into an auditable structured record, then uses dimension-specific agents to score academic impact, fabrication realizability, and novelty. We also construct a 60-paper expert-annotated benchmark for validation and scale the framework to 4,158 papers. FlexSciEval reduces overall mean absolute error by 10.4% compared with direct LLM evaluation on the benchmark annotated by experts, although gains vary by model and dimension. These results indicate that grounding LLM evaluation in structured and dimension-specific evidence improves the reliability of automated scientific assessment in the field of flexible electronics, providing a practical basis for more reliable agent-based evaluation in experimental device research in the future.
%U https://aclanthology.org/2026.realm-1.87/
%P 1243-1262
Markdown (Informal)
[FlexSciEval: Structure-Grounded Multi-agent Evaluation for Flexible Electronics Research](https://aclanthology.org/2026.realm-1.87/) (Li et al., REALM 2026)
ACL