@inproceedings{xiao-etal-2026-lunar,
title = "Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of {LLM}s in Lunar Exploration Scenarios",
author = "Xiao, Xin-Yu and
Tian, Ye and
Yin, Erwei and
He, Zhixian and
Wang, Shiqi and
Liu, Yalei and
Xia, Qianchen",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.83/",
pages = "1668--1705",
ISBN = "979-8-89176-395-1",
abstract = "The increasing complexity of lunar exploration calls for intelligent systems capable of supporting autonomous operations and scientific decision-making under uncertain and resource-limited conditions. Advances in large language models (LLMs) create new opportunities for mission planning, but their reliability in dynamic, safety-critical environments remains insufficiently evaluated. Existing benchmarks focus on static, context-independent reasoning tasks and fail to capture the constraints and dependencies of lunar missions. To address this gap, we introduce Lunar-Bench, a benchmark designed to assess the task-oriented reasoning and decision-making performance of LLMs through 3,000 tasks derived from mission procedures and documentation. We further propose the Environmental Scenario Indicators, a process-based framework that evaluates safety, efficiency, integrity, and alignment beyond conventional accuracy. Experiments on 36 representative models show that the best achieves 47.8{\%} accuracy compared with 65.1{\%} for human experts. Lunar-Bench and ESI together provide a principled foundation for developing reliable systems for future missions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2026-lunar">
<titleInfo>
<title>Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xin-Yu</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erwei</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhixian</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yalei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianchen</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>The increasing complexity of lunar exploration calls for intelligent systems capable of supporting autonomous operations and scientific decision-making under uncertain and resource-limited conditions. Advances in large language models (LLMs) create new opportunities for mission planning, but their reliability in dynamic, safety-critical environments remains insufficiently evaluated. Existing benchmarks focus on static, context-independent reasoning tasks and fail to capture the constraints and dependencies of lunar missions. To address this gap, we introduce Lunar-Bench, a benchmark designed to assess the task-oriented reasoning and decision-making performance of LLMs through 3,000 tasks derived from mission procedures and documentation. We further propose the Environmental Scenario Indicators, a process-based framework that evaluates safety, efficiency, integrity, and alignment beyond conventional accuracy. Experiments on 36 representative models show that the best achieves 47.8% accuracy compared with 65.1% for human experts. Lunar-Bench and ESI together provide a principled foundation for developing reliable systems for future missions.</abstract>
<identifier type="citekey">xiao-etal-2026-lunar</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.83/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1668</start>
<end>1705</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios
%A Xiao, Xin-Yu
%A Tian, Ye
%A Yin, Erwei
%A He, Zhixian
%A Wang, Shiqi
%A Liu, Yalei
%A Xia, Qianchen
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F xiao-etal-2026-lunar
%X The increasing complexity of lunar exploration calls for intelligent systems capable of supporting autonomous operations and scientific decision-making under uncertain and resource-limited conditions. Advances in large language models (LLMs) create new opportunities for mission planning, but their reliability in dynamic, safety-critical environments remains insufficiently evaluated. Existing benchmarks focus on static, context-independent reasoning tasks and fail to capture the constraints and dependencies of lunar missions. To address this gap, we introduce Lunar-Bench, a benchmark designed to assess the task-oriented reasoning and decision-making performance of LLMs through 3,000 tasks derived from mission procedures and documentation. We further propose the Environmental Scenario Indicators, a process-based framework that evaluates safety, efficiency, integrity, and alignment beyond conventional accuracy. Experiments on 36 representative models show that the best achieves 47.8% accuracy compared with 65.1% for human experts. Lunar-Bench and ESI together provide a principled foundation for developing reliable systems for future missions.
%U https://aclanthology.org/2026.findings-acl.83/
%P 1668-1705
Markdown (Informal)
[Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios](https://aclanthology.org/2026.findings-acl.83/) (Xiao et al., Findings 2026)
ACL
- Xin-Yu Xiao, Ye Tian, Erwei Yin, Zhixian He, Shiqi Wang, Yalei Liu, and Qianchen Xia. 2026. Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios. In Findings of the Association for Computational Linguistics: ACL 2026, pages 1668–1705, San Diego, California, United States. Association for Computational Linguistics.