# ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication

arXiv: https://arxiv.org/abs/2609.16014 · HTML: https://mlsanity.com/paper/2609.16014/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [SemDeDup: Data-efficient learning at web-scale through semantic deduplication](https://mlsanity.com/paper/2303.09540/) (2023)
- [Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs](https://mlsanity.com/paper/2506.14245/) (2025)
- [ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation](https://mlsanity.com/paper/2406.09961/) (2024)
- [SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning](https://mlsanity.com/paper/2409.05556/) (2024)
- [ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation](https://mlsanity.com/paper/2501.06598/) (2025)
- [The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models](https://mlsanity.com/paper/2401.05618/) (2024)
- [Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2505.13445/) (2025)
- [PaperBanana: Automating Academic Illustration for AI Scientists](https://mlsanity.com/paper/2601.23265/) (2026)
- [Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots](https://mlsanity.com/paper/2405.07990/) (2024)
- [VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning](https://mlsanity.com/paper/2511.00391/) (2025)
- [VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models](https://mlsanity.com/paper/2508.09945/) (2025)
- [VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations](https://mlsanity.com/paper/2510.22373/) (2025)
- [ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding](https://mlsanity.com/paper/2505.19076/) (2025)
- [VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation](https://mlsanity.com/paper/2602.05998/) (2026)
- [ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding](https://mlsanity.com/paper/2509.17481/) (2025)

## Abstract (arXiv)

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.