大模型
arxiv.org ·
帮助处于困境中的客户：一个能对话、探查和路由的 LLM 驱动代理
该论文提出一个面向银行客户的 AI 分诊代理，利用 LLM 进行多轮对话、主动提问并将案件按政策路由到对应专家团队。为评估与迭代，作者基于历史数据模拟合成数字孪生客户，生成带标注的真实感对话以覆盖多种场景。论文介绍了建模方法、政策集成、安全护栏与推理框架，并报告该代理在历史案例分诊上分类准确率提升 30.6%，内部领域专家给出较高满意度评价。
AI推荐理由 arXiv 论文（cs.HC），作者团队来自银行场景，摘要给出具体方法（多轮对话、主动探查、政策引导路由）与量化结果（历史案例分类准确率提升 30.6%），并说明用合成数字孪生客户做可扩展评测，信息密度和可验证性较好。局限：摘要未披露基线、样本规模与统计显著性，30.6% 提升的具体口径不明；满意度来自内部专家主观报告，非线上真实效果。
72
正文
Computer Science > Human-Computer Interaction
arXiv:2605.16268 (cs)
[Submitted on 31 Mar 2026 (v1), last revised 23 Sep 2026 (this version, v2)]
Title:Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes
Authors:Alankar Atreya, Stefan Sylvius Wagner, Devesh Batra, Robert Hankache, Cristovao Iglesias Jr, Patrick Sinclair, Giulio Pelosio, Michael McMillan, Greig A. Cowan, Raad Khraishi
View a PDF of the paper titled Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes, by Alankar Atreya and 9 other authors
View PDF
HTML (experimental)
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.
Subjects:
Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:
arXiv:2605.16268 [cs.HC]
(or
arXiv:2605.16268v2 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2605.16268
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Alankar Atreya [view email]
[v1]
Tue, 31 Mar 2026 15:07:20 UTC (88 KB)
[v2]
Wed, 23 Sep 2026 12:21:35 UTC (88 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes, by Alankar Atreya and 9 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.HC
new
|
recent
| 2026-05
Change to browse by:
cs
cs.AI
cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)