@inproceedings{mazumdar-2026-runtime,
title = "Runtime Verification of Dimensional Semantics in Checkpointed Large Language Model Tool Workflows",
author = "Mazumdar, Aditya",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.54/",
pages = "800--806",
ISBN = "979-8-89176-485-9",
abstract = "Tool schemas can validate each language-model-generated call while still allowing quantity identity to disappear during a longer workflow. A model may read 250 milliseconds, checkpoint a bare scalar, and later pass 250 to a destination expecting seconds. We call this loss of executable unit and identity metadata semantic scalarization. We present DIMLOCK, a small runtime that carries quantities as opaque references, resolves exact compatible conversions, and rejects cross-dimensional references before destination execution. We also introduce a frozen stress protocol with logical checkpoint save/load, same- and cross- dimension distractors, and receipt-backed scoring. Across 36 workflows and 540 controlled fault trials, DIMLOCK contains all 108 primary faults while prose and structured scalar handoffs contain none. A same- dimension identity swap defeats every interface, confirming the boundary of dimension-only enforcement. Native MCP pilots cover 216 Codex trajectories and a balanced 36-trajectory Claude Sonnet replication; tested models usually rejected explicit traps, so we make no prevalence claim. The result is a focused runtime invariant and a reproducible test for a failure class that local tool schemas do not express."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mazumdar-2026-runtime">
<titleInfo>
<title>Runtime Verification of Dimensional Semantics in Checkpointed Large Language Model Tool Workflows</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Mazumdar</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>Tool schemas can validate each language-model-generated call while still allowing quantity identity to disappear during a longer workflow. A model may read 250 milliseconds, checkpoint a bare scalar, and later pass 250 to a destination expecting seconds. We call this loss of executable unit and identity metadata semantic scalarization. We present DIMLOCK, a small runtime that carries quantities as opaque references, resolves exact compatible conversions, and rejects cross-dimensional references before destination execution. We also introduce a frozen stress protocol with logical checkpoint save/load, same- and cross- dimension distractors, and receipt-backed scoring. Across 36 workflows and 540 controlled fault trials, DIMLOCK contains all 108 primary faults while prose and structured scalar handoffs contain none. A same- dimension identity swap defeats every interface, confirming the boundary of dimension-only enforcement. Native MCP pilots cover 216 Codex trajectories and a balanced 36-trajectory Claude Sonnet replication; tested models usually rejected explicit traps, so we make no prevalence claim. The result is a focused runtime invariant and a reproducible test for a failure class that local tool schemas do not express.</abstract>
<identifier type="citekey">mazumdar-2026-runtime</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.54/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>800</start>
<end>806</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Runtime Verification of Dimensional Semantics in Checkpointed Large Language Model Tool Workflows
%A Mazumdar, Aditya
%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 mazumdar-2026-runtime
%X Tool schemas can validate each language-model-generated call while still allowing quantity identity to disappear during a longer workflow. A model may read 250 milliseconds, checkpoint a bare scalar, and later pass 250 to a destination expecting seconds. We call this loss of executable unit and identity metadata semantic scalarization. We present DIMLOCK, a small runtime that carries quantities as opaque references, resolves exact compatible conversions, and rejects cross-dimensional references before destination execution. We also introduce a frozen stress protocol with logical checkpoint save/load, same- and cross- dimension distractors, and receipt-backed scoring. Across 36 workflows and 540 controlled fault trials, DIMLOCK contains all 108 primary faults while prose and structured scalar handoffs contain none. A same- dimension identity swap defeats every interface, confirming the boundary of dimension-only enforcement. Native MCP pilots cover 216 Codex trajectories and a balanced 36-trajectory Claude Sonnet replication; tested models usually rejected explicit traps, so we make no prevalence claim. The result is a focused runtime invariant and a reproducible test for a failure class that local tool schemas do not express.
%U https://aclanthology.org/2026.realm-1.54/
%P 800-806
Markdown (Informal)
[Runtime Verification of Dimensional Semantics in Checkpointed Large Language Model Tool Workflows](https://aclanthology.org/2026.realm-1.54/) (Mazumdar, REALM 2026)
ACL