@inproceedings{chen-etal-2026-memophishagent,
title = "{M}emo{P}hish{A}gent: Memory-Augmented Multi-Modal {LLM} Agent for Phishing {URL} Detection",
author = "Chen, Xuan and
Liu, Hao and
Yuan, Tao and
Kafai, Mehran and
Habas, Piotr and
Zhang, Xiangyu",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.84/",
pages = "1182--1196",
ISBN = "979-8-89176-394-4",
abstract = "Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. While recent systems incorporate large language models (LLMs), they are still prompt-based, deterministic pipelines that underutilize reasoning capability.We present MemoPhishAgent (MPA), a memory-augmented multi-modal LLM agent that dynamically orchestrates phishing-specific tools and leverages episodic memories of past reasoning trajectories to guide decisions on recurring and novel threats.On two public datasets, MPA outperforms three state-of-the-art (SOTA) baselines, improving recall by 13.6{\%}.To better reflect realistic, user-facing phishing detection performance, we further evaluate MPA on a benchmark of real-world suspicious URLs actively crawled from five social media platforms, where it improves recall by 20{\%}.Detailed analysis shows episodic memory contributes up to 27{\%} recall gain without introducing additional computational overhead.The ablation study confirms the necessity of the agent-based approach compared to prompt-based baselines and validates the effectiveness of our tool design.Finally, MPA is deployed in production, processing $\sim60K$ targeted high-risk URLs weekly, and achieving 91.44{\%} recall, providing proactive protection for millions of customers.Together, our results show that combining multi-modal reasoning with episodic memory yields robust, adaptable phishing detection in realistic user-exposure settings.Our implementation is available at \url{https://github.com/XuanChen-xc/MemoPhishAgent.git}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-memophishagent">
<titleInfo>
<title>MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehran</namePart>
<namePart type="family">Kafai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Habas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Zhang</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</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, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. While recent systems incorporate large language models (LLMs), they are still prompt-based, deterministic pipelines that underutilize reasoning capability.We present MemoPhishAgent (MPA), a memory-augmented multi-modal LLM agent that dynamically orchestrates phishing-specific tools and leverages episodic memories of past reasoning trajectories to guide decisions on recurring and novel threats.On two public datasets, MPA outperforms three state-of-the-art (SOTA) baselines, improving recall by 13.6%.To better reflect realistic, user-facing phishing detection performance, we further evaluate MPA on a benchmark of real-world suspicious URLs actively crawled from five social media platforms, where it improves recall by 20%.Detailed analysis shows episodic memory contributes up to 27% recall gain without introducing additional computational overhead.The ablation study confirms the necessity of the agent-based approach compared to prompt-based baselines and validates the effectiveness of our tool design.Finally, MPA is deployed in production, processing \sim60K targeted high-risk URLs weekly, and achieving 91.44% recall, providing proactive protection for millions of customers.Together, our results show that combining multi-modal reasoning with episodic memory yields robust, adaptable phishing detection in realistic user-exposure settings.Our implementation is available at https://github.com/XuanChen-xc/MemoPhishAgent.git.</abstract>
<identifier type="citekey">chen-etal-2026-memophishagent</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.84/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1182</start>
<end>1196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
%A Chen, Xuan
%A Liu, Hao
%A Yuan, Tao
%A Kafai, Mehran
%A Habas, Piotr
%A Zhang, Xiangyu
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F chen-etal-2026-memophishagent
%X Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. While recent systems incorporate large language models (LLMs), they are still prompt-based, deterministic pipelines that underutilize reasoning capability.We present MemoPhishAgent (MPA), a memory-augmented multi-modal LLM agent that dynamically orchestrates phishing-specific tools and leverages episodic memories of past reasoning trajectories to guide decisions on recurring and novel threats.On two public datasets, MPA outperforms three state-of-the-art (SOTA) baselines, improving recall by 13.6%.To better reflect realistic, user-facing phishing detection performance, we further evaluate MPA on a benchmark of real-world suspicious URLs actively crawled from five social media platforms, where it improves recall by 20%.Detailed analysis shows episodic memory contributes up to 27% recall gain without introducing additional computational overhead.The ablation study confirms the necessity of the agent-based approach compared to prompt-based baselines and validates the effectiveness of our tool design.Finally, MPA is deployed in production, processing \sim60K targeted high-risk URLs weekly, and achieving 91.44% recall, providing proactive protection for millions of customers.Together, our results show that combining multi-modal reasoning with episodic memory yields robust, adaptable phishing detection in realistic user-exposure settings.Our implementation is available at https://github.com/XuanChen-xc/MemoPhishAgent.git.
%U https://aclanthology.org/2026.acl-industry.84/
%P 1182-1196
Markdown (Informal)
[MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection](https://aclanthology.org/2026.acl-industry.84/) (Chen et al., ACL 2026)
ACL