We introduce a novel dual-path agentic framework for robust misleading chart question answering</p>\n","updatedAt":"2026-07-16T00:13:07.458Z","author":{"_id":"656c5b5cfa91c816094cecaf","avatarUrl":"/avatars/25e58c53bc2a14f05307023d45129246.svg","fullname":"Yushi SUN","name":"Yushi98","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8405777812004089},"editors":["Yushi98"],"editorAvatarUrls":["/avatars/25e58c53bc2a14f05307023d45129246.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2603.28583","authors":[{"_id":"6a57904f4f78ed6a77dc001e","name":"Yanjie Zhang","hidden":false},{"_id":"6a57904f4f78ed6a77dc001f","name":"Yafei Li","hidden":false},{"_id":"6a57904f4f78ed6a77dc0020","name":"Rui Sheng","hidden":false},{"_id":"6a57904f4f78ed6a77dc0021","name":"Zixin Chen","hidden":false},{"_id":"6a57904f4f78ed6a77dc0022","name":"Yanna Lin","hidden":false},{"_id":"6a57904f4f78ed6a77dc0023","name":"Huamin Qu","hidden":false},{"_id":"6a57904f4f78ed6a77dc0024","name":"Lei Chen","hidden":false},{"_id":"6a57904f4f78ed6a77dc0025","name":"Yushi Sun","hidden":false}],"publishedAt":"2026-07-14T00:00:00.000Z","submittedOnDailyAt":"2026-07-15T00:00:00.000Z","title":"Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering","submittedOnDailyBy":{"_id":"656c5b5cfa91c816094cecaf","avatarUrl":"/avatars/25e58c53bc2a14f05307023d45129246.svg","isPro":false,"fullname":"Yushi SUN","user":"Yushi98","type":"user","name":"Yushi98"},"summary":"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.","upvotes":3,"discussionId":"6a57904f4f78ed6a77dc0026","organization":{"_id":"63355133edc1a61aecf74b0e","name":"HKUST","fullname":"HKUST","avatar":"https://www.gravatar.com/avatar/4a4318de793d2c187cb6f312e9d0e7bc?d=retro&size=100"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"656c5b5cfa91c816094cecaf","avatarUrl":"/avatars/25e58c53bc2a14f05307023d45129246.svg","isPro":false,"fullname":"Yushi SUN","user":"Yushi98","type":"user"},{"_id":"64bce857796f20daad639795","avatarUrl":"/avatars/36d46ab089bcac562f98fbd0448895db.svg","isPro":false,"fullname":"Dylan","user":"Dylannnnnnnn","type":"user"},{"_id":"677e8b330ef2084985c0a4f5","avatarUrl":"/avatars/d34bbc7cdd9a006c73c85e85ad53429a.svg","isPro":false,"fullname":"Yanjie Zhang","user":"doudouwer","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"63355133edc1a61aecf74b0e","name":"HKUST","fullname":"HKUST","avatar":"https://www.gravatar.com/avatar/4a4318de793d2c187cb6f312e9d0e7bc?d=retro&size=100"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2603/2603.28583.md","query":{}}">
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering
Abstract
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.
Community
We introduce a novel dual-path agentic framework for robust misleading chart question answering
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2603.28583 in a model README.md to link it from this page.
Cite arxiv.org/abs/2603.28583 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2603.28583 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.