{"total":23,"rows":[{"id":"2405.00332","title":"A Careful Examination of Large Language Model Performance on Grade School Arithmetic","created":"2024-05-01","cited_by_count":191,"area":"lr"},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"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":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2402.11541","title":"Large Language Models Can Better Understand Knowledge Graphs Than We Thought","created":"2024-02-18","cited_by_count":10,"area":"lr"},{"id":"2510.02386","title":"On The Fragility of Benchmark Contamination Detection in Reasoning Models","created":"2025-09-30","cited_by_count":9,"area":"lr"},{"id":"2508.08833","title":"An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems","created":"2025-08-12","cited_by_count":8,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2504.02810","title":"Generative Evaluation of Complex Reasoning in Large Language Models","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2607.17384","title":"Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift","created":"2026-07-19","cited_by_count":5,"area":"lr"},{"id":"2502.14155","title":"Giving AI Personalities Leads to More Human-Like Reasoning","created":"2025-02-19","cited_by_count":3,"area":"lr"},{"id":"2503.11614","title":"Neutralizing Bias in LLM Reasoning using Entailment Graphs","created":"2025-03-14","cited_by_count":3,"area":"lr"},{"id":"2508.13003","title":"EvolMathEval: Towards Evolvable Benchmarks for Mathematical Reasoning via Evolutionary Testing","created":"2025-08-18","cited_by_count":3,"area":"lr"},{"id":"2503.13988","title":"Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam Tasks","created":"2025-03-18","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":"2505.14313","title":"Teaching Small Language Models to Learn Logic through Meta-Learning","created":"2025-05-20","cited_by_count":1,"area":"lr"},{"id":"2508.19035","title":"Investigating Advanced Reasoning of Large Language Models via Black-Box Environment Interaction","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2511.02627","title":"DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning","created":"2025-11-04","cited_by_count":1,"area":"lr"},{"id":"2604.04852","title":"Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2608.03388","title":"Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2610.16133","title":"Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}