{"total":32,"rows":[{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2412.13540","title":"Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning","created":"2024-12-18","cited_by_count":19,"area":"lr"},{"id":"2508.10523","title":"Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies","created":"2025-08-14","cited_by_count":17,"area":"lr"},{"id":"2501.10674","title":"Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!","created":"2025-01-18","cited_by_count":15,"area":"lr"},{"id":"2509.01822","title":"When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference","created":"2025-09-01","cited_by_count":12,"area":"lr"},{"id":"2504.05258","title":"Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models","created":"2025-04-07","cited_by_count":10,"area":"lr"},{"id":"2409.12437","title":"Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data","created":"2024-09-19","cited_by_count":8,"area":"lr"},{"id":"2505.19927","title":"TCP: a Benchmark for Temporal Constraint-Based Planning","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2505.16088","title":"Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"id":"2505.17572","title":"USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2407.05434","title":"LTLBench: Towards Benchmarks for Evaluating Temporal Reasoning in Large Language Models","created":"2024-07-07","cited_by_count":4,"area":"lr"},{"id":"2503.05891","title":"MastermindEval: A Simple But Scalable Reasoning Benchmark","created":"2025-03-07","cited_by_count":4,"area":"lr"},{"id":"2504.07646","title":"On the Temporal Question-Answering Capabilities of Large Language Models Over Anonymized Data","created":"2025-04-10","cited_by_count":2,"area":"lr"},{"id":"2601.05549","title":"Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval","created":"2026-01-09","cited_by_count":2,"area":"lr"},{"id":"2603.09512","title":"Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2603.20133","title":"Reasoning Gets Harder for LLMs Inside A Dialogue","created":"2026-03-20","cited_by_count":2,"area":"lr"},{"id":"2511.13095","title":"BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models","created":"2025-11-17","cited_by_count":1,"area":"lr"},{"id":"2512.07218","title":"NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models","created":"2025-12-08","cited_by_count":1,"area":"lr"},{"id":"2601.14658","title":"Say Anything but This: When Tokenizer Betrays Reasoning in LLMs","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2603.19017","title":"What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2605.18380","title":"QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2606.27378","title":"Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2608.15507","title":"Do Language Models Consistently Encode the Current Year?","created":"2026-08-16","cited_by_count":1,"area":"lr"},{"id":"2507.08501","title":"From Language to Logic: A Bi-Level Framework for Structured Reasoning","created":"2025-07-11","cited_by_count":0,"area":"lr"},{"id":"2509.16720","title":"Time to Revist Exact Match","created":"2025-09-20","cited_by_count":0,"area":"lr"},{"id":"2509.22343","title":"Transformers Can Learn Connectivity in Some Graphs but Not Others","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2605.14636","title":"Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.15071","title":"On the Cultural Anachronism and Temporal Reasoning in Vision Language Models","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2608.12348","title":"Can Large Language Models Reason about Event-Time Stream-Processing Semantics?","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2610.02549","title":"Evaluating Multi-Dimensional Generalization of Large Language Models in Temporal Extraction Tasks","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.14073","title":"Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}