@inproceedings{malolan-le-2026-predefined,
title = "Predefined-Tool Execution for Reliable {LLM} Agents in Semiconductor Lot Analysis",
author = "Malolan, Nirupama Vijayaraghavan and
Le, Duc V.",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.102/",
pages = "1765--1787",
ISBN = "979-8-89176-460-6",
abstract = "LLM agents for structured data analysis rely on dynamic query generation, in which the model synthesises tool calls at runtime. This introduces failures such as fabricated dataset references, unsupported operations, and incorrect results, which existing mitigations reduce but do not eliminate. We propose predefined-tool execution as an architectural alternative in which the language model selects and parameterises tools from a fixed, schema-validated registry. We formalise the approach using typed tool specifications and prove executability and hallucination-suppression properties under assumptions. We complement the architecture with a Numerical Faithfulness Checker that verifies quantitative claims against pre-computed ground truth, and evaluate the system on a domain-specific benchmark using four language-model backbones. The suppression property follows from the validation layer under those assumptions, and held across all 276 evaluated agent executions involving 23 queries, four backbones and three runs. Mean exact-plan-match rates ranged from 50.7 to 53.6 per cent, with a between-backbone spread within a single backbone. Because exact plan match penalises valid but non-minimal plans, it is a strict lower bound on task correctness. Given only three runs per backbone, comparisons are descriptive, not evidence of equivalence The on-premise open-weight backbones performed comparably to commercial ones on the measured metrics, supporting confidential deployments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="malolan-le-2026-predefined">
<titleInfo>
<title>Predefined-Tool Execution for Reliable LLM Agents in Semiconductor Lot Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nirupama</namePart>
<namePart type="given">Vijayaraghavan</namePart>
<namePart type="family">Malolan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duc</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Le</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 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>LLM agents for structured data analysis rely on dynamic query generation, in which the model synthesises tool calls at runtime. This introduces failures such as fabricated dataset references, unsupported operations, and incorrect results, which existing mitigations reduce but do not eliminate. We propose predefined-tool execution as an architectural alternative in which the language model selects and parameterises tools from a fixed, schema-validated registry. We formalise the approach using typed tool specifications and prove executability and hallucination-suppression properties under assumptions. We complement the architecture with a Numerical Faithfulness Checker that verifies quantitative claims against pre-computed ground truth, and evaluate the system on a domain-specific benchmark using four language-model backbones. The suppression property follows from the validation layer under those assumptions, and held across all 276 evaluated agent executions involving 23 queries, four backbones and three runs. Mean exact-plan-match rates ranged from 50.7 to 53.6 per cent, with a between-backbone spread within a single backbone. Because exact plan match penalises valid but non-minimal plans, it is a strict lower bound on task correctness. Given only three runs per backbone, comparisons are descriptive, not evidence of equivalence The on-premise open-weight backbones performed comparably to commercial ones on the measured metrics, supporting confidential deployments.</abstract>
<identifier type="citekey">malolan-le-2026-predefined</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.102/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1765</start>
<end>1787</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predefined-Tool Execution for Reliable LLM Agents in Semiconductor Lot Analysis
%A Malolan, Nirupama Vijayaraghavan
%A Le, Duc V.
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F malolan-le-2026-predefined
%X LLM agents for structured data analysis rely on dynamic query generation, in which the model synthesises tool calls at runtime. This introduces failures such as fabricated dataset references, unsupported operations, and incorrect results, which existing mitigations reduce but do not eliminate. We propose predefined-tool execution as an architectural alternative in which the language model selects and parameterises tools from a fixed, schema-validated registry. We formalise the approach using typed tool specifications and prove executability and hallucination-suppression properties under assumptions. We complement the architecture with a Numerical Faithfulness Checker that verifies quantitative claims against pre-computed ground truth, and evaluate the system on a domain-specific benchmark using four language-model backbones. The suppression property follows from the validation layer under those assumptions, and held across all 276 evaluated agent executions involving 23 queries, four backbones and three runs. Mean exact-plan-match rates ranged from 50.7 to 53.6 per cent, with a between-backbone spread within a single backbone. Because exact plan match penalises valid but non-minimal plans, it is a strict lower bound on task correctness. Given only three runs per backbone, comparisons are descriptive, not evidence of equivalence The on-premise open-weight backbones performed comparably to commercial ones on the measured metrics, supporting confidential deployments.
%U https://aclanthology.org/2026.emnlp-industry.102/
%P 1765-1787
Markdown (Informal)
[Predefined-Tool Execution for Reliable LLM Agents in Semiconductor Lot Analysis](https://aclanthology.org/2026.emnlp-industry.102/) (Malolan & Le, EMNLP 2026)
ACL