@inproceedings{chen-etal-2026-tasks,
title = "From Tasks to Teams: A Risk-First Evaluation Framework for Multi-Agent {LLM} Systems in Finance",
author = "Chen, Zichen and
Chen, Jianda and
Chen, Jiaao and
Sra, Misha",
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.1934/",
doi = "10.18653/v1/2026.findings-acl.1934",
pages = "38819--38857",
ISBN = "979-8-89176-395-1",
abstract = "Current financial benchmarks prioritize large language models (LLMs) for task accuracy and portfolio returns, yet overlook risks arising from multi-agent cooperation, tool-sharing, and real-world financial actions. We introduce M-SAEA, a Multi-agent, Safety-Aware Evaluation Agent that audits LLM teams without fine-tuning, deploying ten probes across four layers: model, workflow, interaction, and system, to yield a continuous risk vector and natural-language rationale. Evaluated across three high-stakes tasks (finance management, webshop automation, transactional services) with six prominent models, M-SAEA (i) identifies unsafe trajectories with minimal false positives, (ii) reveals latent risks (e.g., temporal staleness) that are not addressed by standard metrics, and (iii) provides granular, actionable scores for balancing safety and latency pre-deployment. By quantifying safety as a model-agnostic metric, M-SAEA reorients evaluation from individual tasks to collaborative teams, offering a robust template for risk-first assessment of agentic AI in finance and beyond."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-tasks">
<titleInfo>
<title>From Tasks to Teams: A Risk-First Evaluation Framework for Multi-Agent LLM Systems in Finance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zichen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianda</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Misha</namePart>
<namePart type="family">Sra</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>Current financial benchmarks prioritize large language models (LLMs) for task accuracy and portfolio returns, yet overlook risks arising from multi-agent cooperation, tool-sharing, and real-world financial actions. We introduce M-SAEA, a Multi-agent, Safety-Aware Evaluation Agent that audits LLM teams without fine-tuning, deploying ten probes across four layers: model, workflow, interaction, and system, to yield a continuous risk vector and natural-language rationale. Evaluated across three high-stakes tasks (finance management, webshop automation, transactional services) with six prominent models, M-SAEA (i) identifies unsafe trajectories with minimal false positives, (ii) reveals latent risks (e.g., temporal staleness) that are not addressed by standard metrics, and (iii) provides granular, actionable scores for balancing safety and latency pre-deployment. By quantifying safety as a model-agnostic metric, M-SAEA reorients evaluation from individual tasks to collaborative teams, offering a robust template for risk-first assessment of agentic AI in finance and beyond.</abstract>
<identifier type="citekey">chen-etal-2026-tasks</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1934</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1934/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>38819</start>
<end>38857</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Tasks to Teams: A Risk-First Evaluation Framework for Multi-Agent LLM Systems in Finance
%A Chen, Zichen
%A Chen, Jianda
%A Chen, Jiaao
%A Sra, Misha
%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 chen-etal-2026-tasks
%X Current financial benchmarks prioritize large language models (LLMs) for task accuracy and portfolio returns, yet overlook risks arising from multi-agent cooperation, tool-sharing, and real-world financial actions. We introduce M-SAEA, a Multi-agent, Safety-Aware Evaluation Agent that audits LLM teams without fine-tuning, deploying ten probes across four layers: model, workflow, interaction, and system, to yield a continuous risk vector and natural-language rationale. Evaluated across three high-stakes tasks (finance management, webshop automation, transactional services) with six prominent models, M-SAEA (i) identifies unsafe trajectories with minimal false positives, (ii) reveals latent risks (e.g., temporal staleness) that are not addressed by standard metrics, and (iii) provides granular, actionable scores for balancing safety and latency pre-deployment. By quantifying safety as a model-agnostic metric, M-SAEA reorients evaluation from individual tasks to collaborative teams, offering a robust template for risk-first assessment of agentic AI in finance and beyond.
%R 10.18653/v1/2026.findings-acl.1934
%U https://aclanthology.org/2026.findings-acl.1934/
%U https://doi.org/10.18653/v1/2026.findings-acl.1934
%P 38819-38857
Markdown (Informal)
[From Tasks to Teams: A Risk-First Evaluation Framework for Multi-Agent LLM Systems in Finance](https://aclanthology.org/2026.findings-acl.1934/) (Chen et al., Findings 2026)
ACL