{"total":88,"rows":[{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2503.04176","title":"TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records","created":"2025-03-06","cited_by_count":34,"area":null},{"id":"2602.13530","title":"REMem: Reasoning with Episodic Memory in Language Agent","created":"2026-02-13","cited_by_count":23,"area":null},{"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":"2501.03040","title":"ChronoSense: Exploring Temporal Understanding in Large Language Models with Time Intervals of Events","created":"2025-01-06","cited_by_count":18,"area":null},{"id":"2407.03525","title":"UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization","created":"2024-07-03","cited_by_count":17,"area":null},{"id":"2508.10523","title":"Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies","created":"2025-08-14","cited_by_count":17,"area":"lr"},{"id":"2602.13272","title":"TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks","created":"2026-02-05","cited_by_count":17,"area":"agents"},{"id":"2407.04108","title":"Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs","created":"2024-07-04","cited_by_count":15,"area":"safety"},{"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":"2504.02107","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","created":"2025-04-02","cited_by_count":15,"area":null},{"id":"2505.20243","title":"It's High Time: A Survey of Temporal Question Answering","created":"2025-05-26","cited_by_count":14,"area":null},{"id":"2409.13338","title":"Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2510.09869","title":"NarraBench: A Comprehensive Framework for Narrative Benchmarking","created":"2025-10-10","cited_by_count":13,"area":null},{"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":"2503.17073","title":"A Study into Investigating Temporal Robustness of LLMs","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2601.04745","title":"KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions","created":"2026-01-08","cited_by_count":11,"area":null},{"id":"2411.09105","title":"VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models","created":"2024-11-14","cited_by_count":10,"area":null},{"id":"2503.14190","title":"Inferring Events from Time Series using Language Models","created":"2025-03-18","cited_by_count":10,"area":null},{"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":"2510.23853","title":"Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception","created":"2025-10-27","cited_by_count":9,"area":"agents"},{"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":"2410.09870","title":"ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2505.19927","title":"TCP: a Benchmark for Temporal Constraint-Based Planning","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2510.01025","title":"Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2506.03984","title":"Around the World in 24 Hours: Probing LLM Knowledge of Time and Place","created":"2025-06-04","cited_by_count":7,"area":null},{"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":"2505.19533","title":"ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models","created":"2025-05-26","cited_by_count":6,"area":null},{"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":"2505.22112","title":"Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2509.12273","title":"LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences","created":"2025-09-14","cited_by_count":5,"area":null},{"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":"2506.07270","title":"Question Answering under Temporal Conflict: Evaluating and Organizing Evolving Knowledge with LLMs","created":"2025-06-08","cited_by_count":4,"area":null},{"id":"2507.00914","title":"Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications","created":"2025-07-01","cited_by_count":4,"area":"agents"},{"id":"2503.03258","title":"Exploring the Potential of Large Language Models as Predictors in Dynamic Text-Attributed Graphs","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2606.23196","title":"When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2412.13377","title":"DateLogicQA: Benchmarking Temporal Biases in Large Language Models","created":"2024-12-17","cited_by_count":2,"area":null},{"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":"2508.08827","title":"TiMoE: Time-Aware Mixture of Language Experts","created":"2025-08-12","cited_by_count":2,"area":null},{"id":"2510.16980","title":"Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2510.19172","title":"When Facts Change: Probing LLMs on Evolving Knowledge with evolveQA","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2510.27080","title":"Adapting Large Language Models to Emerging Cybersecurity using Retrieval Augmented Generation","created":"2025-10-31","cited_by_count":2,"area":"rag"},{"id":"2511.07722","title":"Critical Confabulation: Can LLMs Hallucinate for Social Good?","created":"2025-11-11","cited_by_count":2,"area":null},{"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":"2604.18177","title":"STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2606.20959","title":"Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2502.01220","title":"Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2508.11163","title":"MobQA: A Benchmark Dataset for Semantic Understanding of Human Mobility Data through Question Answering","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2509.00975","title":"Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning","created":"2025-08-31","cited_by_count":1,"area":null},{"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":"2608.00991","title":"SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2608.08512","title":"Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document Understanding","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2608.09124","title":"ChronoState: Hidden Elapsed-Time Conditioning for Temporal-State Action Selection in Frozen-Backbone Language Models","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.15507","title":"Do Language Models Consistently Encode the Current Year?","created":"2026-08-16","cited_by_count":1,"area":"lr"},{"id":"2506.12148","title":"Hatevolution: What Static Benchmarks Don't Tell Us","created":"2025-06-13","cited_by_count":0,"area":null},{"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":"2510.16685","title":"Structured yet Bounded Temporal Understanding in Large Language Models","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2510.24719","title":"Iti-Validator: A Guardrail Framework for Validating and Correcting LLM-Generated Itineraries","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2512.06590","title":"Towards Efficient Hypergraph and Multi-LLM Agent Recommender Systems","created":"2025-12-06","cited_by_count":0,"area":"agents"},{"id":"2601.14951","title":"TempViz: On the Evaluation of Temporal Knowledge in Text-to-Image Models","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.05361","title":"PACE: A Personalized Adaptive Curriculum Engine for 9-1-1 Call-taker Training","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.16382","title":"LiFT: How to Enable In-Context Learning for Longitudinal Modelling","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.23027","title":"A Systematic Approach for Large Language Models Debugging","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.08766","title":"UserGPT Technical Report","created":"2026-05-09","cited_by_count":0,"area":null},{"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":"2606.05194","title":"Temporal Preference Concepts and their Functions in a Large Language Model","created":"2026-05-11","cited_by_count":0,"area":"mechinterp"},{"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":"2608.12343","title":"Lost in Historical Time? A Polish History Matura Benchmark for Large Language Models","created":"2026-06-03","cited_by_count":0,"area":null},{"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":"2609.02482","title":"How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytelling","created":"2026-09-02","cited_by_count":0,"area":null},{"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":"2610.09944","title":"AgentTime: Can Agents Estimate and Control Their Own Runtime?","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"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"},{"id":"2610.15712","title":"TL;QR: Querying Temporal Discursive Patterns in Textual Corpora","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18126","title":"Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}