Paper Detail

SGA: Plug&Play Geometric Verification for Educational Video Synthesis

Lopez Jhon, Hinojosa Carlos, Ghanem Bernard

arxiv Score 14.8

Published 2026-07-20 · First seen 2026-07-21

General AI

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 x pipeline configurations.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{jhon2026sga,
  title = {SGA: Plug\&Play Geometric Verification for Educational Video Synthesis},
  author = {Lopez Jhon and Hinojosa Carlos and Ghanem Bernard},
  year = {2026},
  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},
  url = {https://arxiv.org/abs/2607.18116},
  keywords = {cs.AI, cs.CV, cs.GR, cs.MA, cs.MM},
  eprint = {2607.18116},
  archiveprefix = {arXiv},
}

Metadata

{}