穿越幻象：一种双路径代理框架用于鲁棒的误导图表问答
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering
AI总结：
本文提出ChartCynics双路径框架，通过分离感知与验证，利用诊断视觉路径和OCR驱动数据路径解决图表误导问题，提升模型鲁棒性。
摘要：
尽管视觉语言模型（VLMs）取得成功，但误导图表仍是重大挑战，因其具有欺骗性视觉结构和扭曲的数据表示。我们提出了ChartCynics，一种代理双路径框架，通过“怀疑”推理范式揭示视觉欺骗。与整体模型不同，ChartCynics将感知与验证分离：诊断视觉路径通过战略性ROI裁剪捕捉结构异常（例如翻转的轴），而OCR驱动的数据路径确保数值基础。为解决跨模态冲突，我们引入了通过两阶段协议优化的代理总结器：Oracle引导的SFT用于推理蒸馏和Deception-aware GRPO用于对抗对齐。该流程有效惩罚视觉陷阱并强制逻辑一致性。在两个基准上的评估显示，ChartCynics在准确率上达到74.43%和64.55%，比Qwen3-VL-8B基础模型提升了约29%，优于最先进的专有模型。我们的结果表明，专门的代理工作流可以赋予较小的开源模型更强的鲁棒性，为可信图表解释建立新基础。
英文摘要：
Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations. We present ChartCynics, an agentic dual-path framework designed to unmask visual deception via a "skeptical" reasoning paradigm. Unlike holistic models, ChartCynics decouples perception from verification: a Diagnostic Vision Path captures structural anomalies (e.g., inverted axes) through strategic ROI cropping, while an OCR-Driven Data Path ensures numerical grounding. To resolve cross-modal conflicts, we introduce an Agentic Summarizer optimized via a two-stage protocol: Oracle-Informed SFT for reasoning distillation and Deception-Aware GRPO for adversarial alignment. This pipeline effectively penalizes visual traps and enforces logical consistency. Evaluations on two benchmarks show that ChartCynics achieves 74.43% and 64.55% accuracy, providing an absolute performance boost of ~29% over the Qwen3-VL-8B backbone, outperforming state-of-the-art proprietary models. Our results demonstrate that specialized agentic workflows can grant smaller open-source models superior robustness, establishing a new foundation for trustworthy chart interpretation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
