<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-failure">
    <titleInfo>
        <title>Failure Modes in Agentic AI: From Reproducible Triggers and Diagnostics to Reliable Fixes</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zoey</namePart>
        <namePart type="given">Sha</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zihan</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hejie</namePart>
        <namePart type="family">Cui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Manling</namePart>
        <namePart type="family">Li</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 2026 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ana</namePart>
            <namePart type="family">Marasović</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Goran</namePart>
            <namePart type="family">Glavaš</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">979-8-89176-463-7</identifier>
    </relatedItem>
    <abstract>Foundation-model agents are being deployed faster than the community can characterize how they fail. In barely two years they have moved into browsing, software engineering, computer use, scientific discovery, and embodied control, where reliability is governed by long-horizon, closed-loop interaction that current single-turn evaluation paradigms rarely capture. Failures (error cascades, reward hacking, mode and reasoning collapse, memory drift, and over-reasoning loops) still lack a shared vocabulary, reproducible triggers, and comparable diagnostics. This cutting-edge tutorial gives a systematic, mechanism-first account of agentic failure modes across four axes: (1) environments and infrastructure, (2) training dynamics, (3) evaluation and red teaming, and (4) test-time scaling and adaptation, with safety threaded throughout. Attendees leave with reproducible triggers, comparable diagnostic protocols, and verifiable mitigations.</abstract>
    <identifier type="citekey">li-etal-2026-failure</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-tutorials.1/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1</start>
            <end>1</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Failure Modes in Agentic AI: From Reproducible Triggers and Diagnostics to Reliable Fixes
%A Li, Zoey Sha
%A Wang, Zihan
%A Cui, Hejie
%A Li, Manling
%Y Marasović, Ana
%Y Glavaš, Goran
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-463-7
%F li-etal-2026-failure
%X Foundation-model agents are being deployed faster than the community can characterize how they fail. In barely two years they have moved into browsing, software engineering, computer use, scientific discovery, and embodied control, where reliability is governed by long-horizon, closed-loop interaction that current single-turn evaluation paradigms rarely capture. Failures (error cascades, reward hacking, mode and reasoning collapse, memory drift, and over-reasoning loops) still lack a shared vocabulary, reproducible triggers, and comparable diagnostics. This cutting-edge tutorial gives a systematic, mechanism-first account of agentic failure modes across four axes: (1) environments and infrastructure, (2) training dynamics, (3) evaluation and red teaming, and (4) test-time scaling and adaptation, with safety threaded throughout. Attendees leave with reproducible triggers, comparable diagnostic protocols, and verifiable mitigations.
%U https://aclanthology.org/2026.emnlp-tutorials.1/
%P 1-1

Markdown (Informal)

[Failure Modes in Agentic AI: From Reproducible Triggers and Diagnostics to Reliable Fixes](https://aclanthology.org/2026.emnlp-tutorials.1/) (Li et al., EMNLP 2026)

• Failure Modes in Agentic AI: From Reproducible Triggers and Diagnostics to Reliable Fixes (Li et al., EMNLP 2026)

ACL

• Zoey Sha Li, Zihan Wang, Hejie Cui, and Manling Li. 2026. Failure Modes in Agentic AI: From Reproducible Triggers and Diagnostics to Reliable Fixes. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, pages 1–1, Budapest, Hungary. Association for Computational Linguistics.