<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-etal-2025-preemptive">
    <titleInfo>
        <title>Preemptive Detection and Correction of Misaligned Actions in LLM Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haishuo</namePart>
        <namePart type="family">Fang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaodan</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Iryna</namePart>
        <namePart type="family">Gurevych</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Deploying LLM-based agents in real-life applications often faces a critical challenge: the misalignment between agents’ behavior and user intent. Such misalignment may lead agents to unintentionally execute some critical actions that carry negative outcomes (e.g., accidentally triggering a buy-now in web shopping), resulting in undesirable or even irreversible consequences. Although addressing these issues is crucial, the preemptive detection and correction of misaligned actions remains relatively underexplored. To fill this gap, we introduce InferAct, a novel approach that leverages the belief reasoning ability of LLMs, grounded in Theory-of-Mind, to detect misaligned actions. Once the misalignment is detected, InferAct alerts users for timely correction, preventing adverse outcomes and enhancing the reliability of LLM agents’ decision-making processes. Experiments on three widely used tasks demonstrate InferAct achieves up to 20% improvements on Marco-F1 against baselines in misaligned action detection. An in-depth evaluation of misalignment correction further highlights InferAct‘s effectiveness in improving agent alignment.</abstract>
    <identifier type="citekey">fang-etal-2025-preemptive</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.12/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>222</start>
            <end>244</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Preemptive Detection and Correction of Misaligned Actions in LLM Agents
%A Fang, Haishuo
%A Zhu, Xiaodan
%A Gurevych, Iryna
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F fang-etal-2025-preemptive
%X Deploying LLM-based agents in real-life applications often faces a critical challenge: the misalignment between agents’ behavior and user intent. Such misalignment may lead agents to unintentionally execute some critical actions that carry negative outcomes (e.g., accidentally triggering a buy-now in web shopping), resulting in undesirable or even irreversible consequences. Although addressing these issues is crucial, the preemptive detection and correction of misaligned actions remains relatively underexplored. To fill this gap, we introduce InferAct, a novel approach that leverages the belief reasoning ability of LLMs, grounded in Theory-of-Mind, to detect misaligned actions. Once the misalignment is detected, InferAct alerts users for timely correction, preventing adverse outcomes and enhancing the reliability of LLM agents’ decision-making processes. Experiments on three widely used tasks demonstrate InferAct achieves up to 20% improvements on Marco-F1 against baselines in misaligned action detection. An in-depth evaluation of misalignment correction further highlights InferAct‘s effectiveness in improving agent alignment.
%U https://aclanthology.org/2025.emnlp-main.12/
%P 222-244

Markdown (Informal)

[Preemptive Detection and Correction of Misaligned Actions in LLM Agents](https://aclanthology.org/2025.emnlp-main.12/) (Fang et al., EMNLP 2025)

• Preemptive Detection and Correction of Misaligned Actions in LLM Agents (Fang et al., EMNLP 2025)

ACL

• Haishuo Fang, Xiaodan Zhu, and Iryna Gurevych. 2025. Preemptive Detection and Correction of Misaligned Actions in LLM Agents. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 222–244, Suzhou, China. Association for Computational Linguistics.