@inproceedings{wang-etal-2025-benchmark,
title = "Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic {LLM} Evaluation",
author = "Wang, Siyuan and
Long, Zhuohan and
Fan, Zhihao and
Huang, Xuanjing and
Wei, Zhongyu",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.223/",
pages = "3310--3328",
abstract = "This paper presents a benchmark self-evolving framework to dynamically evaluate rapidly advancing Large Language Models (LLMs). We utilize a multi-agent system to reframe new evolving instances with high confidence that extend existing benchmarks. Towards a more scalable, robust and fine-grained evaluation, we implement six reframing operations to construct evolving instances testing LLMs against diverse queries, shortcut biases and probing their problem-solving sub-abilities. With this framework, we extend datasets across general and specific tasks, through various iterations. Experimental results show a performance decline in most LLMs against their original results under scalable and robust evaluations, offering a more accurate reflection of model capabilities alongside our fine-grained evaluation. Besides, our framework widens performance discrepancies both between different models and within the same model across various tasks, facilitating more informed model selection for specific tasks. We hope this framework contributes the research community for continuously evolving benchmarks alongside LLM development."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-benchmark">
<titleInfo>
<title>Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuohan</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihao</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a benchmark self-evolving framework to dynamically evaluate rapidly advancing Large Language Models (LLMs). We utilize a multi-agent system to reframe new evolving instances with high confidence that extend existing benchmarks. Towards a more scalable, robust and fine-grained evaluation, we implement six reframing operations to construct evolving instances testing LLMs against diverse queries, shortcut biases and probing their problem-solving sub-abilities. With this framework, we extend datasets across general and specific tasks, through various iterations. Experimental results show a performance decline in most LLMs against their original results under scalable and robust evaluations, offering a more accurate reflection of model capabilities alongside our fine-grained evaluation. Besides, our framework widens performance discrepancies both between different models and within the same model across various tasks, facilitating more informed model selection for specific tasks. We hope this framework contributes the research community for continuously evolving benchmarks alongside LLM development.</abstract>
<identifier type="citekey">wang-etal-2025-benchmark</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.223/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>3310</start>
<end>3328</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation
%A Wang, Siyuan
%A Long, Zhuohan
%A Fan, Zhihao
%A Huang, Xuanjing
%A Wei, Zhongyu
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F wang-etal-2025-benchmark
%X This paper presents a benchmark self-evolving framework to dynamically evaluate rapidly advancing Large Language Models (LLMs). We utilize a multi-agent system to reframe new evolving instances with high confidence that extend existing benchmarks. Towards a more scalable, robust and fine-grained evaluation, we implement six reframing operations to construct evolving instances testing LLMs against diverse queries, shortcut biases and probing their problem-solving sub-abilities. With this framework, we extend datasets across general and specific tasks, through various iterations. Experimental results show a performance decline in most LLMs against their original results under scalable and robust evaluations, offering a more accurate reflection of model capabilities alongside our fine-grained evaluation. Besides, our framework widens performance discrepancies both between different models and within the same model across various tasks, facilitating more informed model selection for specific tasks. We hope this framework contributes the research community for continuously evolving benchmarks alongside LLM development.
%U https://aclanthology.org/2025.coling-main.223/
%P 3310-3328
Markdown (Informal)
[Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation](https://aclanthology.org/2025.coling-main.223/) (Wang et al., COLING 2025)
ACL