<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mao-2026-thesis">
    <titleInfo>
        <title>Thesis Proposal: When Does an Agent Know It Is Lost? Confidence Trajectory Analysis for Tool-Using LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhenjiang</namePart>
        <namePart type="family">Mao</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">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="given">Diego</namePart>
            <namePart type="family">Rodriguez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ona</namePart>
            <namePart type="family">de Gibert</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">979-8-89176-393-7</identifier>
    </relatedItem>
    <abstract>Large language model (LLM) agents that invoke external tools must make sequences of interdependent decisions, yet existing uncertainty quantification (UQ) methods treat each step in isolation, ignoring how confidence evolves and compounds across a full task trajectory.We propose a framework for trajectory-level confidence analysis in the tool-use agent setting. The thesis pursues three aims: (1) estimating action-level confidence by adapting step-wise UQ to the heterogeneous think-act-observe cycles of tool-using agents; (2) aggregating the diverse action space into semantically coherent action types to enable meaningful trajectory-level analysis; and (3) discovering temporal patterns in the resulting confidence trajectories that reliably predict task success or failure.We ground the work in standard tool-use benchmarks and expect the framework to expose early warning signals for agent failure and offer interpretable diagnostic tools for understanding when and why LLM agents lose confidence, with improved calibration of multi-step agentic pipelines as a secondary benefit.</abstract>
    <identifier type="citekey">mao-2026-thesis</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-srw.78/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>877</start>
            <end>887</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Thesis Proposal: When Does an Agent Know It Is Lost? Confidence Trajectory Analysis for Tool-Using LLMs
%A Mao, Zhenjiang
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%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, United States
%@ 979-8-89176-393-7
%F mao-2026-thesis
%X Large language model (LLM) agents that invoke external tools must make sequences of interdependent decisions, yet existing uncertainty quantification (UQ) methods treat each step in isolation, ignoring how confidence evolves and compounds across a full task trajectory.We propose a framework for trajectory-level confidence analysis in the tool-use agent setting. The thesis pursues three aims: (1) estimating action-level confidence by adapting step-wise UQ to the heterogeneous think-act-observe cycles of tool-using agents; (2) aggregating the diverse action space into semantically coherent action types to enable meaningful trajectory-level analysis; and (3) discovering temporal patterns in the resulting confidence trajectories that reliably predict task success or failure.We ground the work in standard tool-use benchmarks and expect the framework to expose early warning signals for agent failure and offer interpretable diagnostic tools for understanding when and why LLM agents lose confidence, with improved calibration of multi-step agentic pipelines as a secondary benefit.
%U https://aclanthology.org/2026.acl-srw.78/
%P 877-887

Markdown (Informal)

[Thesis Proposal: When Does an Agent Know It Is Lost? Confidence Trajectory Analysis for Tool-Using LLMs](https://aclanthology.org/2026.acl-srw.78/) (Mao, ACL 2026)

• Thesis Proposal: When Does an Agent Know It Is Lost? Confidence Trajectory Analysis for Tool-Using LLMs (Mao, ACL 2026)

ACL

• Zhenjiang Mao. 2026. Thesis Proposal: When Does an Agent Know It Is Lost? Confidence Trajectory Analysis for Tool-Using LLMs. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 877–887, San Diego, California, United States. Association for Computational Linguistics.