@inproceedings{kang-xiong-2025-researcharena,
title = "{R}esearch{A}rena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents",
author = "Kang, Hao and
Xiong, Chenyan",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.303/",
doi = "10.18653/v1/2025.findings-emnlp.303",
pages = "5653--5671",
ISBN = "979-8-89176-335-7",
abstract = "Large language models (LLMs) excel across many natural language processing tasks but face challenges in domain-specific, analytical tasks such as conducting research surveys. This study introduces ResearchArena, a benchmark designed to evaluate LLMs' capabilities in conducting academic surveys{---}a foundational step in academic research. ResearchArena models the process in three stages: (1) information discovery, identifying relevant literature; (2) information selection, evaluating papers' relevance and impact; and (3) information organization, structuring knowledge into hierarchical frameworks such as mind-maps. Notably, mind-map construction is treated as a bonus task, reflecting its supplementary role in survey-writing. To support these evaluations, we construct an offline environment of 12M full-text academic papers and 7.9K survey papers. To ensure ethical compliance, we do not redistribute copyrighted materials; instead, we provide code to construct the environment from the Semantic Scholar Open Research Corpus (S2ORC). Preliminary evaluations reveal that LLM-based approaches underperform compared to simpler keyword-based retrieval methods, though recent reasoning models such as DeepSeek-R1 show slightly better zero-shot performance. These results underscore significant opportunities for advancing LLMs in autonomous research. We open-source the code to construct the ResearchArena benchmark at https://github.com/cxcscmu/ResearchArena."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-xiong-2025-researcharena">
<titleInfo>
<title>ResearchArena: Benchmarking Large Language Models’ Ability to Collect and Organize Information as Research Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyan</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) excel across many natural language processing tasks but face challenges in domain-specific, analytical tasks such as conducting research surveys. This study introduces ResearchArena, a benchmark designed to evaluate LLMs’ capabilities in conducting academic surveys—a foundational step in academic research. ResearchArena models the process in three stages: (1) information discovery, identifying relevant literature; (2) information selection, evaluating papers’ relevance and impact; and (3) information organization, structuring knowledge into hierarchical frameworks such as mind-maps. Notably, mind-map construction is treated as a bonus task, reflecting its supplementary role in survey-writing. To support these evaluations, we construct an offline environment of 12M full-text academic papers and 7.9K survey papers. To ensure ethical compliance, we do not redistribute copyrighted materials; instead, we provide code to construct the environment from the Semantic Scholar Open Research Corpus (S2ORC). Preliminary evaluations reveal that LLM-based approaches underperform compared to simpler keyword-based retrieval methods, though recent reasoning models such as DeepSeek-R1 show slightly better zero-shot performance. These results underscore significant opportunities for advancing LLMs in autonomous research. We open-source the code to construct the ResearchArena benchmark at https://github.com/cxcscmu/ResearchArena.</abstract>
<identifier type="citekey">kang-xiong-2025-researcharena</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.303</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.303/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>5653</start>
<end>5671</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ResearchArena: Benchmarking Large Language Models’ Ability to Collect and Organize Information as Research Agents
%A Kang, Hao
%A Xiong, Chenyan
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F kang-xiong-2025-researcharena
%X Large language models (LLMs) excel across many natural language processing tasks but face challenges in domain-specific, analytical tasks such as conducting research surveys. This study introduces ResearchArena, a benchmark designed to evaluate LLMs’ capabilities in conducting academic surveys—a foundational step in academic research. ResearchArena models the process in three stages: (1) information discovery, identifying relevant literature; (2) information selection, evaluating papers’ relevance and impact; and (3) information organization, structuring knowledge into hierarchical frameworks such as mind-maps. Notably, mind-map construction is treated as a bonus task, reflecting its supplementary role in survey-writing. To support these evaluations, we construct an offline environment of 12M full-text academic papers and 7.9K survey papers. To ensure ethical compliance, we do not redistribute copyrighted materials; instead, we provide code to construct the environment from the Semantic Scholar Open Research Corpus (S2ORC). Preliminary evaluations reveal that LLM-based approaches underperform compared to simpler keyword-based retrieval methods, though recent reasoning models such as DeepSeek-R1 show slightly better zero-shot performance. These results underscore significant opportunities for advancing LLMs in autonomous research. We open-source the code to construct the ResearchArena benchmark at https://github.com/cxcscmu/ResearchArena.
%R 10.18653/v1/2025.findings-emnlp.303
%U https://aclanthology.org/2025.findings-emnlp.303/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.303
%P 5653-5671
Markdown (Informal)
[ResearchArena: Benchmarking Large Language Models’ Ability to Collect and Organize Information as Research Agents](https://aclanthology.org/2025.findings-emnlp.303/) (Kang & Xiong, Findings 2025)
ACL