{"total":15,"rows":[{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2604.14164","title":"How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2602.13367","title":"Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts","created":"2026-02-13","cited_by_count":6,"area":"lr"},{"id":"2511.16205","title":"ChemLabs on ChemO: A Multi-Agent System for Multimodal Reasoning on IChO 2025","created":"2025-11-20","cited_by_count":3,"area":"lr"},{"id":"2602.06319","title":"Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2605.15177","title":"OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2510.16259","title":"Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense","created":"2025-10-17","cited_by_count":2,"area":"lr"},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2510.22340","title":"DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry","created":"2025-10-25","cited_by_count":1,"area":"lr"},{"id":"2511.15355","title":"HEAD-QA v2: Expanding a Healthcare Benchmark for Reasoning","created":"2025-11-19","cited_by_count":1,"area":"lr"},{"id":"2601.04996","title":"AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms?","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2605.07806","title":"Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2608.16033","title":"$R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets","created":"2026-08-17","cited_by_count":0,"area":"lr"},{"id":"2608.29632","title":"InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information","created":"2026-08-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}