METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling
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 in accuracy 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Financial AnalysisSimilar Papers 제목 키워드 기반
ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering
Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textua…
Visual Question AnsweringChart Question AnsweringVisual ReasoningPlotEdit: Natural Language-Driven Accessible Chart Editing in PDFs via Multimodal LLM Agents
Chart visualizations, while essential for data interpretation and communication, are predominantly accessible only as images in PDFs, lacking source data tables and stylistic information. To enable effective editing of c…
AttributeTable ExtractionChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution
Large Language Models (LLMs) can perform chart question-answering tasks but often generate unverified hallucinated responses. Existing answer attribution methods struggle to ground responses in source charts due to limit…
Chart Question AnsweringQuestion AnsweringRe-RankingRetrieval+1ChartAgent: A Chart Understanding Framework with Tool Integrated Reasoning
With their high information density and intuitive readability, charts have become the de facto medium for data analysis and communication across disciplines. Recent multimodal large language models (MLLMs) have made nota…
Instance SegmentationBeyond Description: A Multimodal Agent Framework for Insightful Chart Summarization
Chart summarization is crucial for enhancing data accessibility and the efficient consumption of information. However, existing methods, including those with Multimodal Large Language Models (MLLMs), primarily focus on l…