<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aghzal-etal-2026-llm">
    <titleInfo>
        <title>Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mohamed</namePart>
        <namePart type="family">Aghzal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gregory</namePart>
        <namePart type="given">J</namePart>
        <namePart type="family">Stein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziyu</namePart>
        <namePart type="family">Yao</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 (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizon tasks. Existing evaluations focus primarily on end-to-end success, offering limited insight into where failures arise. We propose a hierarchical planning framework that analyzes web agents across three layers (i.e., high-level planning, low-level execution, and re-planning), enabling process-based evaluation of reasoning, grounding, and recovery. Our experiments show that structured Planning Domain Definition Language (PDDL) plans produce more concise and goal-directed strategies than natural language (NL) plans, but low-level execution remains the dominant bottleneck. These results indicate that improving perceptual grounding and adaptive control, not only high-level reasoning, is critical for achieving human-level reliability. This hierarchical perspective provides a principled foundation for diagnosing and advancing LLM web agents.</abstract>
    <identifier type="citekey">aghzal-etal-2026-llm</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.1483/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>32157</start>
            <end>32180</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective
%A Aghzal, Mohamed
%A Stein, Gregory J.
%A Yao, Ziyu
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F aghzal-etal-2026-llm
%X Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizon tasks. Existing evaluations focus primarily on end-to-end success, offering limited insight into where failures arise. We propose a hierarchical planning framework that analyzes web agents across three layers (i.e., high-level planning, low-level execution, and re-planning), enabling process-based evaluation of reasoning, grounding, and recovery. Our experiments show that structured Planning Domain Definition Language (PDDL) plans produce more concise and goal-directed strategies than natural language (NL) plans, but low-level execution remains the dominant bottleneck. These results indicate that improving perceptual grounding and adaptive control, not only high-level reasoning, is critical for achieving human-level reliability. This hierarchical perspective provides a principled foundation for diagnosing and advancing LLM web agents.
%U https://aclanthology.org/2026.acl-long.1483/
%P 32157-32180

Markdown (Informal)

[Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective](https://aclanthology.org/2026.acl-long.1483/) (Aghzal et al., ACL 2026)

• Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective (Aghzal et al., ACL 2026)

ACL

• Mohamed Aghzal, Gregory J. Stein, and Ziyu Yao. 2026. Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 32157–32180, San Diego, California, United States. Association for Computational Linguistics.