作者位次 #2/4ACL 2026Poster· Natural Language Processing
C hart A gent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering
Rachneet Kaur · Nishan Srishankar · Zhen Zeng · Sumitra Ganesh
摘要
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 textual shortcuts. To address this, we introduce ChartAgent, a novel agentic framew...