@inproceedings{atreya-etal-2026-helping,
title = "Helping Customers in Distress: An {LLM}-powered Agent that Converses, Probes, and Routes",
author = "Atreya, Alankar and
Wagner, Stefan Sylvius and
Batra, Devesh and
Hankache, Robert and
Iglesias Jr, Cristov{\~a}o and
Sinclair, Patrick and
Pelosio, Giulio and
McMillan, Michael and
Cowan, Greig A and
Khraishi, Raad",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.33/",
pages = "403--407",
ISBN = "979-8-89176-466-8",
abstract = "Banks receive millions of reports of fraud, scams, and disputed transactions every year, making it challenging to accurately direct customers to the appropriate specialist teams for assistance. The existing manual process driven by humans is slow and stressful for both customers and staff. To address this, we develop a customer-facing AI powered triaging agent that leverages large language models (LLMs) to conduct multi-turn conversations, ask relevant questions, and classify cases for accurate, policy-guided routing, making it embedded in the customer journey. To evaluate and continuously improve the agent, synthetic digital twins of real customers were simulated, generating realistic, labelled dialogues based on historical data to test a wide range of real-world scenarios. This work details the triage agent{'}s modelling approach, integration with policy, safety guardrails and reasoning frameworks, the use of the synthetic agent for scalable evaluation, and findings on the AI system{'}s accuracy, robustness, and compliance. Results show that the agent successfully improves triaging of historical cases, achieving a 30.6{\%} increase in classification accuracy, with high satisfaction levels reported by our subject-matter experts, highlighting how targeted probing can lead to more effective triage in banking operations at scale.{`}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atreya-etal-2026-helping">
<titleInfo>
<title>Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alankar</namePart>
<namePart type="family">Atreya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="given">Sylvius</namePart>
<namePart type="family">Wagner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Devesh</namePart>
<namePart type="family">Batra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Hankache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristovão</namePart>
<namePart type="family">Iglesias Jr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Sinclair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulio</namePart>
<namePart type="family">Pelosio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">McMillan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greig</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Cowan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raad</namePart>
<namePart type="family">Khraishi</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>Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</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">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>Banks receive millions of reports of fraud, scams, and disputed transactions every year, making it challenging to accurately direct customers to the appropriate specialist teams for assistance. The existing manual process driven by humans is slow and stressful for both customers and staff. To address this, we develop a customer-facing AI powered triaging agent that leverages large language models (LLMs) to conduct multi-turn conversations, ask relevant questions, and classify cases for accurate, policy-guided routing, making it embedded in the customer journey. To evaluate and continuously improve the agent, synthetic digital twins of real customers were simulated, generating realistic, labelled dialogues based on historical data to test a wide range of real-world scenarios. This work details the triage agent’s modelling approach, integration with policy, safety guardrails and reasoning frameworks, the use of the synthetic agent for scalable evaluation, and findings on the AI system’s accuracy, robustness, and compliance. Results show that the agent successfully improves triaging of historical cases, achieving a 30.6% increase in classification accuracy, with high satisfaction levels reported by our subject-matter experts, highlighting how targeted probing can lead to more effective triage in banking operations at scale.‘</abstract>
<identifier type="citekey">atreya-etal-2026-helping</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.33/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>403</start>
<end>407</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes
%A Atreya, Alankar
%A Wagner, Stefan Sylvius
%A Batra, Devesh
%A Hankache, Robert
%A Iglesias Jr, Cristovão
%A Sinclair, Patrick
%A Pelosio, Giulio
%A McMillan, Michael
%A Cowan, Greig A.
%A Khraishi, Raad
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F atreya-etal-2026-helping
%X Banks receive millions of reports of fraud, scams, and disputed transactions every year, making it challenging to accurately direct customers to the appropriate specialist teams for assistance. The existing manual process driven by humans is slow and stressful for both customers and staff. To address this, we develop a customer-facing AI powered triaging agent that leverages large language models (LLMs) to conduct multi-turn conversations, ask relevant questions, and classify cases for accurate, policy-guided routing, making it embedded in the customer journey. To evaluate and continuously improve the agent, synthetic digital twins of real customers were simulated, generating realistic, labelled dialogues based on historical data to test a wide range of real-world scenarios. This work details the triage agent’s modelling approach, integration with policy, safety guardrails and reasoning frameworks, the use of the synthetic agent for scalable evaluation, and findings on the AI system’s accuracy, robustness, and compliance. Results show that the agent successfully improves triaging of historical cases, achieving a 30.6% increase in classification accuracy, with high satisfaction levels reported by our subject-matter experts, highlighting how targeted probing can lead to more effective triage in banking operations at scale.‘
%U https://aclanthology.org/2026.finnlp-1.33/
%P 403-407
Markdown (Informal)
[Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes](https://aclanthology.org/2026.finnlp-1.33/) (Atreya et al., FinNLP 2026)
ACL
- Alankar Atreya, Stefan Sylvius Wagner, Devesh Batra, Robert Hankache, Cristovão Iglesias Jr, Patrick Sinclair, Giulio Pelosio, Michael McMillan, Greig A Cowan, and Raad Khraishi. 2026. Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 403–407, Budapest, Hungary. Association for Computational Linguistics.