# METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling

arXiv: https://arxiv.org/abs/2502.17651 · HTML: https://mlsanity.com/paper/2502.17651/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 56 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 12 of 12)

- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models](https://mlsanity.com/paper/2408.00724/) (2024)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [ChartLlama: A Multimodal LLM for Chart Understanding and Generation](https://mlsanity.com/paper/2311.16483/) (2023)
- [ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation](https://mlsanity.com/paper/2406.09961/) (2024)
- [ChartBench: A Benchmark for Complex Visual Reasoning in Charts](https://mlsanity.com/paper/2312.15915/) (2023)
- [MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization](https://mlsanity.com/paper/2402.11453/) (2024)
- [Agents' Room: Narrative Generation through Multi-step Collaboration](https://mlsanity.com/paper/2410.02603/) (2024)
- [Scaling LLM Inference with Optimized Sample Compute Allocation](https://mlsanity.com/paper/2410.22480/) (2024)
- [Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks](https://mlsanity.com/paper/2311.01949/) (2023)

## Built on by (most cited first, 30 of 34)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding](https://mlsanity.com/paper/2503.13964/) (2025)
- [Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling](https://mlsanity.com/paper/2508.03404/) (2025)
- [ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering](https://mlsanity.com/paper/2506.10116/) (2025)
- [Dual Latent Memory for Visual Multi-agent System](https://mlsanity.com/paper/2602.00471/) (2026)
- [Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction](https://mlsanity.com/paper/2506.14837/) (2025)
- [AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents](https://mlsanity.com/paper/2607.18754/) (2026)
- [EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation](https://mlsanity.com/paper/2512.24731/) (2025)
- [Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning](https://mlsanity.com/paper/2604.06079/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning](https://mlsanity.com/paper/2601.11957/) (2026)
- [Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation](https://mlsanity.com/paper/2604.10741/) (2026)
- [OpusAnimation: Code-Based Dynamic Chart Generation](https://mlsanity.com/paper/2510.03341/) (2025)
- [MARTI-MARS2: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation](https://mlsanity.com/paper/2602.07848/) (2026)
- [Vision-Guided Iterative Refinement for Frontend Code Generation](https://mlsanity.com/paper/2604.05839/) (2026)
- [Multi-Turn Agentic Scientific Literature Search via Workflow Induction](https://mlsanity.com/paper/2607.00597/) (2026)
- [NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs](https://mlsanity.com/paper/2601.06126/) (2026)
- [Robotic Policy Adaptation via Weight-Space Meta-Learning](https://mlsanity.com/paper/2606.07217/) (2026)
- [BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery](https://mlsanity.com/paper/2606.20997/) (2026)
- [Long-Horizon Embodied Decision-Making via Multimodal Memory Compression](https://mlsanity.com/paper/2608.01456/) (2026)
- [A2R2: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement](https://mlsanity.com/paper/2507.20890/) (2025)
- [Agentic Mixed-Source Multi-Modal Misinformation Detection with Adaptive Test-Time Scaling](https://mlsanity.com/paper/2603.02519/) (2026)
- [Beyond Pixels: Introspective and Interactive Grounding for Visualization Agents](https://mlsanity.com/paper/2604.21134/) (2026)
- [A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation](https://mlsanity.com/paper/2605.19316/) (2026)
- [Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning](https://mlsanity.com/paper/2606.08231/) (2026)
- [Imperfect Visual Verification for Code Edition : A Case Study on TikZ](https://mlsanity.com/paper/2606.15693/) (2026)

## Abstract (arXiv)

Chart generation aims to generate code to produce charts satisfying the desired visual properties, e.g., texts, layout, color, and type. It has great potential to empower the automatic professional report generation in financial analysis, research presentation, education, and healthcare. In this work, we build a vision-language model (VLM) based multi-agent framework for effective automatic chart generation. Generating high-quality charts requires both strong visual design skills and precise coding capabilities that embed the desired visual properties into code. Such a complex multi-modal reasoning process is difficult for direct prompting of VLMs. To resolve these challenges, we propose METAL, a multi-agent framework that decomposes the task of chart generation into the iterative collaboration among specialized agents. METAL achieves 5.2% improvement over the current best result in the chart generation task. The METAL framework exhibits the phenomenon of test-time scaling: its performance increases monotonically as the logarithmic computational budget grows from 512 to 8192 tokens. In addition, we find that separating different modalities during the critique process of METAL boosts the self-correction capability of VLMs in the multimodal context.