<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pedada-etal-2026-shared">
    <titleInfo>
        <title>Shared Selective Persistent Memory for Agentic LLM Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sanjana</namePart>
        <namePart type="family">Pedada</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aditya</namePart>
        <namePart type="family">Dhavala</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Neelraj</namePart>
        <namePart type="given">J</namePart>
        <namePart type="family">Patil</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolai</namePart>
            <namePart type="family">Rozanov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maryam</namePart>
            <namePart type="family">Hashemzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akhil</namePart>
            <namePart type="family">Arora</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">979-8-89176-485-9</identifier>
    </relatedItem>
    <abstract>Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the domain constraints, data schemas, tool configurations, and output preferences that made previous sessions productive. We introduce shared selective persistent memory, an architecture that retains four categories of reusable context — task specifications, data schemas, tool configurations, and output constraints — while discarding session-specific reasoning traces, and that packages them into workspaces transferable across users under role-based access control.\par The resulting cost curve is non-monotonic. In a controlled replication on four public datasets, where a formatting specification is established once and then withheld, no memory completes 0/12 trials at 3.8K input tokens, selective memory completes 12/12 at 3.9K, and full conversation history completes 8/12 at 7.7K. What is kept matters more than how much is kept: the winning configuration costs essentially what the failing one does, and twice as much context does not improve on it. Both differences from no memory survive Bonferroni-corrected exact McNemar tests (p = 0.0005, p = 0.008); selective memory and full history are indistinguishable on completion (p = 0.125) and separate on price. Every no-memory failure is a specification failure and nothing else — the artifacts are structurally sound but do not reproduce a constraint they were never given.\par We implement this in a deployed platform where agents produce git-versioned artifacts from CSV, SQL, REST, and MCP sources. A complementary zero-token data refresh contract decouples generated programs from runtime data, firing on 12/12 trials at a median 0.08s with no model call, while summary-driven data representation costs 97–431x fewer tokens than raw injection. Across 24 recurring enterprise tasks selective memory completes 23/24 against 19/24 and 17/24, though at that sample no pairwise difference reaches significance; there, where users re-specify rather than rely on memory, full history returns no improvement at all despite 9x the input.</abstract>
    <identifier type="citekey">pedada-etal-2026-shared</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.1/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1</start>
            <end>13</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Shared Selective Persistent Memory for Agentic LLM Systems
%A Pedada, Sanjana
%A Dhavala, Aditya
%A Patil, Neelraj J.
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F pedada-etal-2026-shared
%X Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the domain constraints, data schemas, tool configurations, and output preferences that made previous sessions productive. We introduce shared selective persistent memory, an architecture that retains four categories of reusable context — task specifications, data schemas, tool configurations, and output constraints — while discarding session-specific reasoning traces, and that packages them into workspaces transferable across users under role-based access control.\par The resulting cost curve is non-monotonic. In a controlled replication on four public datasets, where a formatting specification is established once and then withheld, no memory completes 0/12 trials at 3.8K input tokens, selective memory completes 12/12 at 3.9K, and full conversation history completes 8/12 at 7.7K. What is kept matters more than how much is kept: the winning configuration costs essentially what the failing one does, and twice as much context does not improve on it. Both differences from no memory survive Bonferroni-corrected exact McNemar tests (p = 0.0005, p = 0.008); selective memory and full history are indistinguishable on completion (p = 0.125) and separate on price. Every no-memory failure is a specification failure and nothing else — the artifacts are structurally sound but do not reproduce a constraint they were never given.\par We implement this in a deployed platform where agents produce git-versioned artifacts from CSV, SQL, REST, and MCP sources. A complementary zero-token data refresh contract decouples generated programs from runtime data, firing on 12/12 trials at a median 0.08s with no model call, while summary-driven data representation costs 97–431x fewer tokens than raw injection. Across 24 recurring enterprise tasks selective memory completes 23/24 against 19/24 and 17/24, though at that sample no pairwise difference reaches significance; there, where users re-specify rather than rely on memory, full history returns no improvement at all despite 9x the input.
%U https://aclanthology.org/2026.realm-1.1/
%P 1-13

Markdown (Informal)

[Shared Selective Persistent Memory for Agentic LLM Systems](https://aclanthology.org/2026.realm-1.1/) (Pedada et al., REALM 2026)

• Shared Selective Persistent Memory for Agentic LLM Systems (Pedada et al., REALM 2026)

ACL

• Sanjana Pedada, Aditya Dhavala, and Neelraj J. Patil. 2026. Shared Selective Persistent Memory for Agentic LLM Systems. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 1–13, Budapest, Hungary. Association for Computational Linguistics.