@inproceedings{dong-etal-2026-etom,
title = "{ETOM}: A Five-Level Benchmark for Evaluating Tool Orchestration within the {MCP} Ecosystem",
author = "Dong, Jia-Kai and
Huang, I-Wei and
Wu, Chun-Tin and
Tsai, Yi-tien",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.75/",
pages = "1453--1488",
ISBN = "979-8-89176-386-9",
abstract = "We introduce ETOM, a five-level benchmark for evaluating multi-hop, end-to-end tool orchestration by LLM agents within a hierarchical Model-Context Protocol (MCP) ecosystem. Existing benchmarks often assess tools in isolation, overlooking challenges such as functional overlap and cross-server orchestration, which can lead to overly optimistic evaluations. ETOM addresses these gaps by constructing ground truth through ``equal function sets'', enabling objective metrics such as F1 score and reducing reliance on LLM-as-a-judge evaluation. Its five-level curriculum systematically tests agent capabilities, from single-tool orchestration to complex cross-server planning, as well as robustness to out-of-scope requests. Experiments reveal that rigid hierarchies can hinder performance without co-designed strategies, and even state-of-the-art agents exhibit systemic weaknesses in robustness. ETOM provides a diagnostic framework to expose these limitations and guide the development of more capable and efficient tool-using agents."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2026-etom">
<titleInfo>
<title>ETOM: A Five-Level Benchmark for Evaluating Tool Orchestration within the MCP Ecosystem</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jia-Kai</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">I-Wei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chun-Tin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-tien</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>We introduce ETOM, a five-level benchmark for evaluating multi-hop, end-to-end tool orchestration by LLM agents within a hierarchical Model-Context Protocol (MCP) ecosystem. Existing benchmarks often assess tools in isolation, overlooking challenges such as functional overlap and cross-server orchestration, which can lead to overly optimistic evaluations. ETOM addresses these gaps by constructing ground truth through “equal function sets”, enabling objective metrics such as F1 score and reducing reliance on LLM-as-a-judge evaluation. Its five-level curriculum systematically tests agent capabilities, from single-tool orchestration to complex cross-server planning, as well as robustness to out-of-scope requests. Experiments reveal that rigid hierarchies can hinder performance without co-designed strategies, and even state-of-the-art agents exhibit systemic weaknesses in robustness. ETOM provides a diagnostic framework to expose these limitations and guide the development of more capable and efficient tool-using agents.</abstract>
<identifier type="citekey">dong-etal-2026-etom</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.75/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>1453</start>
<end>1488</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ETOM: A Five-Level Benchmark for Evaluating Tool Orchestration within the MCP Ecosystem
%A Dong, Jia-Kai
%A Huang, I-Wei
%A Wu, Chun-Tin
%A Tsai, Yi-tien
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F dong-etal-2026-etom
%X We introduce ETOM, a five-level benchmark for evaluating multi-hop, end-to-end tool orchestration by LLM agents within a hierarchical Model-Context Protocol (MCP) ecosystem. Existing benchmarks often assess tools in isolation, overlooking challenges such as functional overlap and cross-server orchestration, which can lead to overly optimistic evaluations. ETOM addresses these gaps by constructing ground truth through “equal function sets”, enabling objective metrics such as F1 score and reducing reliance on LLM-as-a-judge evaluation. Its five-level curriculum systematically tests agent capabilities, from single-tool orchestration to complex cross-server planning, as well as robustness to out-of-scope requests. Experiments reveal that rigid hierarchies can hinder performance without co-designed strategies, and even state-of-the-art agents exhibit systemic weaknesses in robustness. ETOM provides a diagnostic framework to expose these limitations and guide the development of more capable and efficient tool-using agents.
%U https://aclanthology.org/2026.findings-eacl.75/
%P 1453-1488
Markdown (Informal)
[ETOM: A Five-Level Benchmark for Evaluating Tool Orchestration within the MCP Ecosystem](https://aclanthology.org/2026.findings-eacl.75/) (Dong et al., Findings 2026)
ACL