{"total":47,"rows":[{"id":"2411.00836","title":"DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models","created":"2024-10-29","cited_by_count":146,"area":"lr"},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2508.17536","title":"Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?","created":"2025-08-24","cited_by_count":81,"area":"lr"},{"id":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2504.03846","title":"Do LLM Evaluators Prefer Themselves for a Reason?","created":"2025-04-04","cited_by_count":38,"area":"lr"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2510.12697","title":"Multi-Agent Debate for LLM Judges with Adaptive Stability Detection","created":"2025-10-14","cited_by_count":23,"area":"lr"},{"id":"2504.00509","title":"Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?","created":"2025-04-01","cited_by_count":15,"area":"lr"},{"id":"2506.22058","title":"Lost at the Beginning of Reasoning","created":"2025-06-27","cited_by_count":15,"area":"lr"},{"id":"2404.08382","title":"Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think","created":"2024-04-12","cited_by_count":14,"area":"lr"},{"id":"2406.16605","title":"CLEAR: Can Language Models Really Understand Causal Graphs?","created":"2024-06-24","cited_by_count":14,"area":"lr"},{"id":"2609.31142","title":"JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models","created":"2026-09-25","cited_by_count":10,"area":"lr"},{"id":"2502.01159","title":"AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science","created":"2025-02-03","cited_by_count":9,"area":"lr"},{"id":"2409.15454","title":"In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2411.01101","title":"Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems","created":"2024-11-02","cited_by_count":7,"area":"lr"},{"id":"2510.07484","title":"Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs","created":"2025-10-08","cited_by_count":6,"area":"lr"},{"id":"2401.05190","title":"DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs","created":"2024-01-10","cited_by_count":5,"area":"lr"},{"id":"2505.17019","title":"Let Androids Dream of Electric Sheep: A Human-Inspired Image Implication Understanding and Reasoning Framework","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2506.10415","title":"Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?","created":"2025-06-12","cited_by_count":4,"area":"lr"},{"id":"2512.22207","title":"GamiBench: Evaluating Spatial Reasoning and 2D-to-3D Planning Capabilities of MLLMs with Origami Folding Tasks","created":"2025-12-22","cited_by_count":4,"area":"lr"},{"id":"2405.05189","title":"MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning","created":"2024-05-08","cited_by_count":3,"area":"lr"},{"id":"2506.04734","title":"Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design","created":"2025-06-05","cited_by_count":3,"area":"lr"},{"id":"2603.21016","title":"Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO","created":"2026-03-22","cited_by_count":3,"area":"lr"},{"id":"2607.15418","title":"DrawingVQA: A Real-World Benchmark for Multi-Depth Visual-Textual Reasoning on Construction Drawings","created":"2026-07-16","cited_by_count":3,"area":"lr"},{"id":"2504.10090","title":"CameraBench: Benchmarking Visual Reasoning in MLLMs via Photography","created":"2025-04-14","cited_by_count":2,"area":"lr"},{"id":"2507.15378","title":"AlgoSimBench: Identifying Algorithmically Similar Problems for Competitive Programming","created":"2025-07-21","cited_by_count":2,"area":"lr"},{"id":"2601.22228","title":"Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation","created":"2026-01-29","cited_by_count":2,"area":"lr"},{"id":"2602.00127","title":"ALIGN: Aligned Delegation with Performance Guarantees for Multi-Agent LLM Reasoning","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2602.00723","title":"Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2607.08065","title":"When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2502.18435","title":"What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?","created":"2025-02-25","cited_by_count":1,"area":"lr"},{"id":"2511.15355","title":"HEAD-QA v2: Expanding a Healthcare Benchmark for Reasoning","created":"2025-11-19","cited_by_count":1,"area":"lr"},{"id":"2602.05932","title":"Polyglots or Multitudes? Multilingual LLM Answers to Value-laden Multiple-Choice Questions","created":"2026-02-05","cited_by_count":1,"area":"lr"},{"id":"2603.29025","title":"The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2605.15574","title":"MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2608.10908","title":"Order Matters: LVLMs as Judges for Temporal Reasoning in Image Sequences","created":"2026-08-11","cited_by_count":1,"area":"lr"},{"id":"2609.32809","title":"Overwhelmed by Choice: Studying LLM Decision Making at Scale","created":"2026-09-26","cited_by_count":1,"area":"lr"},{"id":"2609.36931","title":"Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation","created":"2026-09-29","cited_by_count":1,"area":"lr"},{"id":"2510.16686","title":"Investigating the Impact of Rationales for LLMs on Natural Language Understanding","created":"2025-10-19","cited_by_count":0,"area":"lr"},{"id":"2511.03768","title":"What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes","created":"2025-11-05","cited_by_count":0,"area":"lr"},{"id":"2604.10034","title":"AI Achieves a Perfect LSAT Score","created":"2026-04-11","cited_by_count":0,"area":"lr"},{"id":"2605.20410","title":"Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2608.15445","title":"Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization","created":"2026-08-15","cited_by_count":0,"area":"lr"},{"id":"2609.09372","title":"What Does MMLU Actually Measure? A Psychometric Audit of Difficulty Structure in Aggregate Benchmark Scores","created":"2026-09-08","cited_by_count":0,"area":"lr"},{"id":"2609.29278","title":"Reasoning Instructions Can Break Answer Decoding in Vision--Language Models","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2610.00437","title":"JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.17777","title":"Beyond Belief Nesting: Rethinking Higher-Order Theory of Mind in Large Language Models","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}