@inproceedings{lopez-etal-2026-sga,
title = "{SGA}: Plug {\&} Play Geometric Verification for Educational Video Synthesis",
author = "Lopez, Jhon and
Hinojosa, Carlos and
Ghanem, Bernard",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.454/",
pages = "9533--9549",
ISBN = "979-8-89176-462-0",
abstract = "Recent work leverages **Large Language Models (LLMs)** to generate executable code for pedagogical animations using libraries such as **Manim**. However, ensuring spatial correctness and visual legibility remains challenging, as existing frameworks emphasize pedagogical content while overlooking geometric occlusions. We propose the **Symbolic Geometric Agent (SGA)**, a plug-and-play module for code-centric animation pipelines that intercepts LLM-generated code, performs partial execution to extract symbolic scene graphs, and applies targeted refinement when spatial conflicts are detected. We further introduce the **Manim Visual Quality Score (MVQS)**, a deterministic rendering-free proxy for spatial integrity. Experiments on the **MMMC-Code** benchmark across four LLM backbones and two agentic pipelines show that SGA achieves a peak MVQS of **73.11** (**Code2Video + GPT-5.1**), corresponding to a **16.1{\%}** relative improvement over the raw baseline, and improves MVQS in **7 of 8** backbone {\texttimes} pipeline configurations. Additionally, we conduct a human evaluation showing that these improvements translate into human preference, with raters preferring SGA over the raw baseline in **84.4{\%}** of comparisons and over a VLM-based critic in **65.0{\%}**."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lopez-etal-2026-sga">
<titleInfo>
<title>SGA: Plug & Play Geometric Verification for Educational Video Synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jhon</namePart>
<namePart type="family">Lopez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Hinojosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernard</namePart>
<namePart type="family">Ghanem</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>Recent work leverages **Large Language Models (LLMs)** to generate executable code for pedagogical animations using libraries such as **Manim**. However, ensuring spatial correctness and visual legibility remains challenging, as existing frameworks emphasize pedagogical content while overlooking geometric occlusions. We propose the **Symbolic Geometric Agent (SGA)**, a plug-and-play module for code-centric animation pipelines that intercepts LLM-generated code, performs partial execution to extract symbolic scene graphs, and applies targeted refinement when spatial conflicts are detected. We further introduce the **Manim Visual Quality Score (MVQS)**, a deterministic rendering-free proxy for spatial integrity. Experiments on the **MMMC-Code** benchmark across four LLM backbones and two agentic pipelines show that SGA achieves a peak MVQS of **73.11** (**Code2Video + GPT-5.1**), corresponding to a **16.1%** relative improvement over the raw baseline, and improves MVQS in **7 of 8** backbone × pipeline configurations. Additionally, we conduct a human evaluation showing that these improvements translate into human preference, with raters preferring SGA over the raw baseline in **84.4%** of comparisons and over a VLM-based critic in **65.0%**.</abstract>
<identifier type="citekey">lopez-etal-2026-sga</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.454/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>9533</start>
<end>9549</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SGA: Plug & Play Geometric Verification for Educational Video Synthesis
%A Lopez, Jhon
%A Hinojosa, Carlos
%A Ghanem, Bernard
%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 lopez-etal-2026-sga
%X Recent work leverages **Large Language Models (LLMs)** to generate executable code for pedagogical animations using libraries such as **Manim**. However, ensuring spatial correctness and visual legibility remains challenging, as existing frameworks emphasize pedagogical content while overlooking geometric occlusions. We propose the **Symbolic Geometric Agent (SGA)**, a plug-and-play module for code-centric animation pipelines that intercepts LLM-generated code, performs partial execution to extract symbolic scene graphs, and applies targeted refinement when spatial conflicts are detected. We further introduce the **Manim Visual Quality Score (MVQS)**, a deterministic rendering-free proxy for spatial integrity. Experiments on the **MMMC-Code** benchmark across four LLM backbones and two agentic pipelines show that SGA achieves a peak MVQS of **73.11** (**Code2Video + GPT-5.1**), corresponding to a **16.1%** relative improvement over the raw baseline, and improves MVQS in **7 of 8** backbone × pipeline configurations. Additionally, we conduct a human evaluation showing that these improvements translate into human preference, with raters preferring SGA over the raw baseline in **84.4%** of comparisons and over a VLM-based critic in **65.0%**.
%U https://aclanthology.org/2026.findings-emnlp.454/
%P 9533-9549
Markdown (Informal)
[SGA: Plug & Play Geometric Verification for Educational Video Synthesis](https://aclanthology.org/2026.findings-emnlp.454/) (Lopez et al., Findings 2026)
ACL