@inproceedings{huang-etal-2026-realfin,
title = "{R}eal{F}in: Benchmarking Agent Workflow Orchestration Beyond {MCP}-Style Tool Connectivity",
author = "Huang, Ying and
Liu, Shuoling and
Chen, Liyuan and
Shi, Jie and
Liang, Jiaqing and
Pengtao, Yang and
Liao, Ying and
Han, Jinyi and
Jiang, Sihang and
Xiao, Yanghua",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.341/",
pages = "7161--7183",
ISBN = "979-8-89176-462-0",
abstract = "Standardized interfaces such as the Model Context Protocol (MCP) make it easier to connect tools to agents, but connection alone is not orchestration. When many related tools are exposed as a flat callable palette, agents must identify relevant tools, resolve substitutes, pass intermediate outputs, and decide when a workflow is complete. We introduce RealFin, a finance-domain diagnostic benchmark for evaluating workflow construction under MCP-style flat tool exposure. RealFin contains 1524 tasks generated from 108 author-designed financial workflow templates over real market, macroeconomic, and company-data APIs. Each task is paired with an executable reference program that specifies one verified solution path, while the 85 agent-callable tools include explicit alternative, dependency, and related-tool metadata to represent non-unique paths, prerequisite tools, and near-neighbor ambiguity. This design supports path-independent answer scoring together with process-level evaluation of tool selection, ordering, parameter planning, entity grounding, temporal grounding, orchestration success, and error recovery. Across ReAct-style flat exposure, retrieval-based exposure, oracle-controlled variants, and progressive tool disclosure, current agents often achieve nonzero answer accuracy while failing to construct reliable workflows. These results suggest that MCP-style tool connectivity needs structured disclosure and workflow-aware evaluation, especially in finance where temporal constraints and overlapping tools are intrinsic."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-realfin">
<titleInfo>
<title>RealFin: Benchmarking Agent Workflow Orchestration Beyond MCP-Style Tool Connectivity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuoling</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liyuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqing</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Pengtao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinyi</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sihang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghua</namePart>
<namePart type="family">Xiao</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Standardized interfaces such as the Model Context Protocol (MCP) make it easier to connect tools to agents, but connection alone is not orchestration. When many related tools are exposed as a flat callable palette, agents must identify relevant tools, resolve substitutes, pass intermediate outputs, and decide when a workflow is complete. We introduce RealFin, a finance-domain diagnostic benchmark for evaluating workflow construction under MCP-style flat tool exposure. RealFin contains 1524 tasks generated from 108 author-designed financial workflow templates over real market, macroeconomic, and company-data APIs. Each task is paired with an executable reference program that specifies one verified solution path, while the 85 agent-callable tools include explicit alternative, dependency, and related-tool metadata to represent non-unique paths, prerequisite tools, and near-neighbor ambiguity. This design supports path-independent answer scoring together with process-level evaluation of tool selection, ordering, parameter planning, entity grounding, temporal grounding, orchestration success, and error recovery. Across ReAct-style flat exposure, retrieval-based exposure, oracle-controlled variants, and progressive tool disclosure, current agents often achieve nonzero answer accuracy while failing to construct reliable workflows. These results suggest that MCP-style tool connectivity needs structured disclosure and workflow-aware evaluation, especially in finance where temporal constraints and overlapping tools are intrinsic.</abstract>
<identifier type="citekey">huang-etal-2026-realfin</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.341/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>7161</start>
<end>7183</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RealFin: Benchmarking Agent Workflow Orchestration Beyond MCP-Style Tool Connectivity
%A Huang, Ying
%A Liu, Shuoling
%A Chen, Liyuan
%A Shi, Jie
%A Liang, Jiaqing
%A Pengtao, Yang
%A Liao, Ying
%A Han, Jinyi
%A Jiang, Sihang
%A Xiao, Yanghua
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F huang-etal-2026-realfin
%X Standardized interfaces such as the Model Context Protocol (MCP) make it easier to connect tools to agents, but connection alone is not orchestration. When many related tools are exposed as a flat callable palette, agents must identify relevant tools, resolve substitutes, pass intermediate outputs, and decide when a workflow is complete. We introduce RealFin, a finance-domain diagnostic benchmark for evaluating workflow construction under MCP-style flat tool exposure. RealFin contains 1524 tasks generated from 108 author-designed financial workflow templates over real market, macroeconomic, and company-data APIs. Each task is paired with an executable reference program that specifies one verified solution path, while the 85 agent-callable tools include explicit alternative, dependency, and related-tool metadata to represent non-unique paths, prerequisite tools, and near-neighbor ambiguity. This design supports path-independent answer scoring together with process-level evaluation of tool selection, ordering, parameter planning, entity grounding, temporal grounding, orchestration success, and error recovery. Across ReAct-style flat exposure, retrieval-based exposure, oracle-controlled variants, and progressive tool disclosure, current agents often achieve nonzero answer accuracy while failing to construct reliable workflows. These results suggest that MCP-style tool connectivity needs structured disclosure and workflow-aware evaluation, especially in finance where temporal constraints and overlapping tools are intrinsic.
%U https://aclanthology.org/2026.findings-emnlp.341/
%P 7161-7183
Markdown (Informal)
[RealFin: Benchmarking Agent Workflow Orchestration Beyond MCP-Style Tool Connectivity](https://aclanthology.org/2026.findings-emnlp.341/) (Huang et al., Findings 2026)
ACL
- Ying Huang, Shuoling Liu, Liyuan Chen, Jie Shi, Jiaqing Liang, Yang Pengtao, Ying Liao, Jinyi Han, Sihang Jiang, and Yanghua Xiao. 2026. RealFin: Benchmarking Agent Workflow Orchestration Beyond MCP-Style Tool Connectivity. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 7161–7183, Budapest, Hungary. Association for Computational Linguistics.