{"total":24,"rows":[{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246,"area":"lr"},{"id":"2502.13124","title":"NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions","created":"2025-02-18","cited_by_count":84,"area":"lr"},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2411.04109","title":"Self-Consistency Preference Optimization","created":"2024-11-06","cited_by_count":50,"area":"lr"},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2502.09457","title":"A Survey of Multilingual Reasoning in Language Models","created":"2025-02-13","cited_by_count":33,"area":"lr"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2501.03681","title":"SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment","created":"2025-01-07","cited_by_count":18,"area":"lr"},{"id":"2510.07300","title":"Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2510.27269","title":"Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?","created":"2025-10-31","cited_by_count":12,"area":"lr"},{"id":"2506.05850","title":"Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models","created":"2025-06-06","cited_by_count":11,"area":"lr"},{"id":"2504.15241","title":"MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety","created":"2025-04-21","cited_by_count":9,"area":"lr"},{"id":"2601.13262","title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","created":"2026-01-19","cited_by_count":9,"area":"lr"},{"id":"2405.01345","title":"The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights","created":"2024-05-02","cited_by_count":7,"area":"lr"},{"id":"2502.17956","title":"Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments","created":"2025-02-25","cited_by_count":6,"area":"lr"},{"id":"2602.05940","title":"R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning","created":"2026-02-05","cited_by_count":5,"area":"lr"},{"id":"2601.08267","title":"Med-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2607.00485","title":"Efficient Multilingual Reasoning Transfer via Progressive Code-Switching","created":"2026-07-01","cited_by_count":2,"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":"2607.11736","title":"MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2608.06347","title":"RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2610.04899","title":"Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}