{"total":36,"rows":[{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336,"area":"lr"},{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215,"area":"lr"},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2406.09170","title":"Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning","created":"2024-06-13","cited_by_count":88,"area":"lr"},{"id":"2202.04800","title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning","created":"2022-02-10","cited_by_count":38,"area":"lr"},{"id":"2506.09943","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","created":"2025-06-11","cited_by_count":35,"area":"lr"},{"id":"2406.09175","title":"ReMI: A Dataset for Reasoning with Multiple Images","created":"2024-06-13","cited_by_count":30,"area":"lr"},{"id":"2406.06196","title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages","created":"2024-06-10","cited_by_count":28,"area":"lr"},{"id":"2505.07889","title":"BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science","created":"2025-05-11","cited_by_count":16,"area":"lr"},{"id":"2209.02552","title":"From Black Boxes to Conversations: Incorporating XAI in a Conversational Agent","created":"2022-09-06","cited_by_count":14,"area":"lr"},{"id":"2206.09203","title":"Interactive Visual Reasoning under Uncertainty","created":"2022-06-18","cited_by_count":8,"area":"lr"},{"id":"2211.02950","title":"The Legal Argument Reasoning Task in Civil Procedure","created":"2022-11-05","cited_by_count":8,"area":"lr"},{"id":"2306.07743","title":"V-LoL: A Diagnostic Dataset for Visual Logical Learning","created":"2023-06-13","cited_by_count":8,"area":"lr"},{"id":"2502.20758","title":"Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truth","created":"2025-02-28","cited_by_count":7,"area":"lr"},{"id":"2602.20571","title":"CausalReasoningBenchmark: A Real-World Benchmark for Disentangled Evaluation of Causal Identification and Estimation","created":"2026-02-24","cited_by_count":6,"area":"lr"},{"id":"2406.11061","title":"A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning","created":"2024-06-16","cited_by_count":4,"area":"lr"},{"id":"2510.04141","title":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2603.09678","title":"EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages","created":"2026-03-10","cited_by_count":4,"area":"lr"},{"id":"2509.23219","title":"WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2402.08498","title":"\"Reasoning\" with Rhetoric: On the Style-Evidence Tradeoff in LLM-Generated Counter-Arguments","created":"2024-02-13","cited_by_count":2,"area":"lr"},{"id":"2210.12478","title":"DiscoSense: Commonsense Reasoning with Discourse Connectives","created":"2022-10-22","cited_by_count":1,"area":"lr"},{"id":"2502.13207","title":"Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2605.12131","title":"Rollout Cards: A Reproducibility Standard for Agent Research","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.23170","title":"Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2605.29170","title":"UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2603.09993","title":"CEI: A Benchmark for Evaluating Pragmatic Reasoning in Language Models","created":"2026-02-14","cited_by_count":0,"area":"lr"},{"id":"2605.03900","title":"Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2605.22734","title":"ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.04442","title":"MemoryDocDataSet: A Benchmark for Joint Conversational Memory and Long Document Reasoning","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2606.10740","title":"When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.24950","title":"MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios","created":"2026-06-23","cited_by_count":0,"area":"lr"},{"id":"2607.07883","title":"Nigeria Machinery: A Low-Resource Industrial Dataset with a Domain-Grounded Reasoning Layer","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2609.00018","title":"SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diagram QA and Chain-of-Thought Reasoning Traces","created":"2026-08-20","cited_by_count":0,"area":"lr"},{"id":"2609.09203","title":"OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows","created":"2026-09-05","cited_by_count":0,"area":"lr"},{"id":"2610.12954","title":"MathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure Generation","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}