Metraipolis › archive › dc_86bb458507dd

ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication — arXiv:2609.16014

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16014
License (as archived)
CC0-1.0
Archived
2026-10-15T19:17:04.343Z
SHA-256 of the archived text
31217bd2f4acc4b02e08e18d7ea34597e871c9fd2b5041870304140483900ff2
Stable URL of this page
https://metraipolis.com/documento/dc_86bb458507dd

How to cite

ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication — arXiv:2609.16014 — arXiv (en), https://arxiv.org/abs/2609.16014 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_86bb458507dd (Metraipolis archive dc_86bb458507dd, sha256 31217bd2f4acc4b02e08e18d7ea34597e871c9fd2b5041870304140483900ff2)
BibTeX
@misc{dc86bb458507dd,
  title = {ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication — arXiv:2609.16014},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16014},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_86bb458507dd; sha256 31217bd2f4acc4b02e08e18d7ea34597e871c9fd2b5041870304140483900ff2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16014. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper addresses the challenge of generating high-quality academic charts that match the visual standards of human-authored papers. While existing AI agents can produce well-structured text and code, their generated visualizations often lack the stylistic and semantic fidelity of human designs. Advanced coding agents that employ self-reflection mechanisms exhibit poor visual reasoning and limited reflection following, resulting in sparse reward signals that severely undermine their reinforcement learning (RL). We propose ViCo, a training framework for visual-oriented coding that employs iterative reflections to align generated chart images progressively with the reference. We first introduce a self-supervised warm-up stage, which augments Monte Carlo Tree Search with consistency-based pruning to synthesize high-quality reflection trajectories, ensuring that each coding step strictly follows the outcomes of prior reflections. A multi-step RL algorithm is then developed, using counterfactual baselines to estimate advantage for reflection and action steps within each refinement cycle, thereby addressing the reward sparsity. To enable efficient reward in massive training, we propose an automatic, multifaceted evaluation framework that assesses charts' style, layout, and semantic consistency via a hierarchical heterogeneous layout graph structure. Experiments on three public benchmarks demonstrate that ViCo, trained on an 8B model, achieves performance close to proprietary LLMs with adequate reflection capabilities.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Graphics (cs.GR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.16014 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:32:32.790Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).