ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization

• URL: http://arxiv.org/abs/2605.12159v1
• Date: Tue, 12 May 2026 14:09:48 GMT
• Title: ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization
• Abstract summary: Algorithm visualization (AV) helps students build mental models by animating algorithm execution states.<n>Recent LLM-based systems such as CODE2VIDEO generate AV videos in an end-to-end manner.<n>This paradigm requires the system to simultaneously simulate algorithm flow and satisfy video rendering constraints.<n>We propose ALGOGEN, a novel paradigm that decouples execution from visualizations.
• Score: 58.40239235264315
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Algorithm Visualization (AV) helps students build mental models by animating algorithm execution states. Recent LLM-based systems such as CODE2VIDEO generate AV videos in an end-to-end manner. However, this paradigm requires the system to simultaneously simulate algorithm flow and satisfy video rendering constraints, such as element layout and color schemes. This complex task induces LLM hallucinations, resulting in reduced execution success rates, element overlap, and inter-frame inconsistencies. To address these challenges, we propose ALGOGEN, a novel paradigm that decouples algorithm execution from rendering. We first introduce Visualization Trace Algebra (VTA), a monoid over algorithm visual states and operations. The LLM then generates a Python tracker that simulates algorithm flow and outputs VTA-JSON traces, a JSON encoding of VTA. For rendering, we define a Rendering Style Language (RSL) to templatize algorithm layouts. A deterministic renderer then compiles algorithm traces with RSL into Manim, LaTeX/TikZ, or Three.js outputs. Evaluated on a LeetCode AV benchmark of 200 tasks, ALGOGEN achieves an average success rate improvement of 17.3% compared to end-to-end methods, with 99.8% versus 82.5%. These results demonstrate that our decoupling paradigm effectively mitigates LLM hallucinations in complex AV tasks, providing a more reliable solution for automated generation of high-quality algorithm visualizations. Demo videos and code are available in the project repository.

Related papers

• Clustering and Token Denoising for Faster and More Robust VLMs [0.6999740786886536]
  We introduce ClustRS, a two-part, training-free algorithm for robust token pruning.<n> Experimental results on the ScienceQA-IMG and MM-VET benchmarks show our method outperforms attention- and diversity-based methods.<n>Our study demonstrates a simple yet powerful alternative to both score-only and diversity-only pruning rules, paving the way for compute-efficient and noise-resilient VLM deployment.
  arXiv  Detail & Related papers  (2026-08-19T11:20:26Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs [88.68484904214142]
  We introduce Patch-as-Decodable Token (PaDT) to generate both textual and diverse visual outputs.<n>Central to PaDT are Visual Reference Tokens (VRTs), derived from visual patch embeddings of query images.<n>We show PaDT consistently achieves state-of-the-art performance, even compared with significantly larger MLLM models.
  arXiv  Detail & Related papers  (2025-10-02T12:23:57Z)
• Evaluating Efficiency and Novelty of LLM-Generated Code for Graph Analysis [0.1274452325287335]
  Large Language Models (LLMs) are increasingly used to automate software development.<n>We present a comprehensive study of LLMs' ability to generate efficient C implementations of graph-analysis routines.<n>The potential for these models to invent transformative algorithmic techniques represents a compelling frontier for future research.
  arXiv  Detail & Related papers  (2025-07-09T00:46:30Z)
• DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs [124.52164183968145]
  We present DyMU, an efficient, training-free framework that reduces the computational burden of vision-language models (VLMs)<n>Our approach comprises two key components. First, Dynamic Token Merging (DToMe) reduces the number of visual token embeddings by merging similar tokens based on image complexity.<n>Second, Virtual Token Unmerging (VTU) simulates the expected token sequence for large language models (LLMs) by efficiently reconstructing the attention dynamics of a full sequence.
  arXiv  Detail & Related papers  (2025-04-23T18:38:18Z)
• AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning [19.68349294206012]
  Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos.<n>We propose a training-free adaptive inference method for multi-modal LLMs that can accommodate a broad range of efficiency requirements.
  arXiv  Detail & Related papers  (2024-12-04T11:47:57Z)
• SIGMA:Sinkhorn-Guided Masked Video Modeling [69.31715194419091]
  Sinkhorn-guided Masked Video Modelling ( SIGMA) is a novel video pretraining method. We distribute features of space-time tubes evenly across a limited number of learnable clusters. Experimental results on ten datasets validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations.
  arXiv  Detail & Related papers  (2024-07-22T08:04:09Z)
• Code Simulation Challenges for Large Language Models [6.970495767499435]
  This work studies to what extent Large Language Models (LLMs) can simulate coding and algorithmic tasks. We introduce benchmarks for straight-line programs, code that contains critical paths, and approximate and redundant instructions. We propose a novel off-the-shelf prompting method, Chain of Simulation (CoSm), which instructs LLMs to simulate code execution line by line/follow the pattern of compilers.
  arXiv  Detail & Related papers  (2024-01-17T09:23:59Z)
• United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videos [37.53372462270059]
  Given multiple videos of the same task, procedure learning addresses identifying the key-steps and determining their order to perform the task. This makes key-steps discovery challenging as the algorithms lack inter-videos perspective. We propose an unsupervised Graph-based Procedure Learning framework that represents all the videos of a task as a graph to obtain both intra-video and inter-videos context.
  arXiv  Detail & Related papers  (2023-11-06T21:33:56Z)
• ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers [60.6418431624873]
  Large language models (LLMs) excel at implementing code from functionality descriptions but struggle with algorithmic problems. We propose ALGO, a framework that synthesizes Algorithmic programs with LLM-Generated Oracles to guide the generation and verify their correctness. Experiments show that when equipped with ALGO, we achieve an 8x better one-submission pass rate over the Codex model and a 2.6x better one-submission pass rate over CodeT.
  arXiv  Detail & Related papers  (2023-05-24T00:10:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.