DRAGON : A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
Anirudh Iyengar Kaniyar Narayana Iyengar · Tampu Ravi Kumar · Gaurav Najpande · Manan Suri · Dinesh Manocha · Puneet Mathur · Vivek Gupta
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Anirudh Iyengar Kaniyar Narayana Iyengar · Tampu Ravi Kumar · Gaurav Najpande · Manan Suri · Dinesh Manocha · Puneet Mathur · Vivek Gupta
Anirudh Iyengar Kaniyar Narayana Iyengar · Tampu Ravi Kumar · Manan Suri · Raviteja Bommireddy · Dinesh Manocha · Puneet Mathur · Vivek Gupta
Diagram question answering (Diagram QA) requires reasoning-level attribution that links each question-answer pair to all visual regions needed to derive the answer, rather than only the region containing the final response. Creating such structured evidence across diagrams, charts, maps, circuits...
Manan Suri · Puneet Mathur · Nedim Lipka · Franck Dernoncourt · Ryan A. Rossi · Dinesh Manocha
LLM agents with tool-calling capabilities often fail when user instructions are ambiguous or incomplete, leading to incorrect invocations and task failures. Existing approaches operate in unstructured language spaces, generating clarifying questions through prompting strategies that lack principl...
Manan Suri · Xiangci Li · Mehdi Shojaie · Songyang Han · Chao-Chun Hsu · Shweta Garg · Aniket Anand Deshmukh · Varun Kumar
Current AI-powered code assistance tools often struggle with ambiguous problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such ambiguous requests are highly correlated with longer trajectorie...