<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2026-st">
    <titleInfo>
        <title>ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bowen</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhou</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wanli</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jingyu</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pingan</namePart>
        <namePart type="family">Gan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haoqian</namePart>
        <namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing methods are designed for generic language workloads and ignore the distinctive structure of GUI interaction traces. We characterize three GUI-specific workload properties — high inter-frame visual redundancy, extremely small UI-element spatial footprints, and near-uniform cross-layer attention sparsity — that cause existing schemes to retain as few as 39% of oracle-important KV pairs at the standard 20% budget. To address this, we propose **ST-Lite**, a training-free compression scheme whose three components each target one property: Trajectory-aware Semantic Gating (TSG) filters redundant historical frames, Component-centric Spatial Saliency (CSS) preserves fine-grained element boundaries, and a flat per-layer budget avoids hierarchical misallocation. Across seven GUI benchmarks and two backbones in the deployment-relevant \ensuremathβ \ensuremathın [10%, 40%] window, **ST-Lite** consistently outperforms all existing compression baselines — matching or exceeding Full Cache task accuracy on the primary backbone at the 20% budget — while delivering up to 2.35× decoding speedup at fivefold compression. Code: https://github.com/94wen94/ST-Lite</abstract>
    <identifier type="citekey">zhou-etal-2026-st</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.455/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>9550</start>
            <end>9586</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents
%A Zhou, Bowen
%A Xu, Zhou
%A Li, Wanli
%A Xiao, Jingyu
%A Gan, Pingan
%A Wang, Haoqian
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zhou-etal-2026-st
%X Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing methods are designed for generic language workloads and ignore the distinctive structure of GUI interaction traces. We characterize three GUI-specific workload properties — high inter-frame visual redundancy, extremely small UI-element spatial footprints, and near-uniform cross-layer attention sparsity — that cause existing schemes to retain as few as 39% of oracle-important KV pairs at the standard 20% budget. To address this, we propose **ST-Lite**, a training-free compression scheme whose three components each target one property: Trajectory-aware Semantic Gating (TSG) filters redundant historical frames, Component-centric Spatial Saliency (CSS) preserves fine-grained element boundaries, and a flat per-layer budget avoids hierarchical misallocation. Across seven GUI benchmarks and two backbones in the deployment-relevant \ensuremathβ \ensuremathın [10%, 40%] window, **ST-Lite** consistently outperforms all existing compression baselines — matching or exceeding Full Cache task accuracy on the primary backbone at the 20% budget — while delivering up to 2.35× decoding speedup at fivefold compression. Code: https://github.com/94wen94/ST-Lite
%U https://aclanthology.org/2026.findings-emnlp.455/
%P 9550-9586

Markdown (Informal)

[ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents](https://aclanthology.org/2026.findings-emnlp.455/) (Zhou et al., Findings 2026)

• ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents (Zhou et al., Findings 2026)

ACL

• Bowen Zhou, Zhou Xu, Wanli Li, Jingyu Xiao, Pingan Gan, and Haoqian Wang. 2026. ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 9550–9586, Budapest, Hungary. Association for Computational Linguistics.