{"total":16,"rows":[{"id":"2504.15279","title":"VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models","created":"2025-04-21","cited_by_count":107,"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":"2402.08939","title":"Premise Order Matters in Reasoning with Large Language Models","created":"2024-02-14","cited_by_count":72,"area":"lr"},{"id":"2502.15652","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","created":"2025-02-21","cited_by_count":51,"area":"lr"},{"id":"2505.14615","title":"SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas","created":"2025-05-20","cited_by_count":33,"area":"lr"},{"id":"2401.17169","title":"Conditional and Modal Reasoning in Large Language Models","created":"2024-01-30","cited_by_count":9,"area":"lr"},{"id":"2406.12546","title":"Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models","created":"2024-06-18","cited_by_count":9,"area":"lr"},{"id":"2502.15725","title":"Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona Interaction","created":"2025-01-28","cited_by_count":5,"area":"lr"},{"id":"2502.12275","title":"Integrating Expert Knowledge into Logical Programs via LLMs","created":"2025-02-17","cited_by_count":3,"area":"lr"},{"id":"2501.13833","title":"On the Reasoning Capacity of AI Models and How to Quantify It","created":"2025-01-23","cited_by_count":2,"area":"lr"},{"id":"2503.07903","title":"Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?","created":"2025-03-10","cited_by_count":2,"area":"lr"},{"id":"2504.12312","title":"Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-based Test Oracles","created":"2025-04-09","cited_by_count":2,"area":"lr"},{"id":"2512.03360","title":"From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation","created":"2025-12-03","cited_by_count":2,"area":"lr"},{"id":"2505.11141","title":"Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2602.14035","title":"FloCA: Towards Faithful and Logically Consistent Flowchart Reasoning","created":"2026-02-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}