{"total":37,"rows":[{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330,"area":"lr"},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203,"area":"lr"},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811,"area":"lr"},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243,"area":"lr"},{"id":"2505.22375","title":"Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition","created":"2025-05-28","cited_by_count":62,"area":"lr"},{"id":"2502.00674","title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","created":"2025-02-02","cited_by_count":54,"area":"lr"},{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2505.15431","title":"Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought","created":"2025-05-21","cited_by_count":29,"area":"lr"},{"id":"2505.21600","title":"R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing","created":"2025-05-27","cited_by_count":29,"area":"lr"},{"id":"2505.14604","title":"Let LRMs Break Free from Overthinking via Self-Braking Tuning","created":"2025-05-20","cited_by_count":27,"area":"lr"},{"id":"2505.13774","title":"Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models","created":"2025-05-19","cited_by_count":23,"area":"lr"},{"id":"2504.03790","title":"Sample, Don't Search: Rethinking Test-Time Alignment for Language Models","created":"2025-04-04","cited_by_count":22,"area":"lr"},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2502.20432","title":"LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory","created":"2025-02-27","cited_by_count":17,"area":"lr"},{"id":"2410.10336","title":"CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning","created":"2024-10-14","cited_by_count":16,"area":"lr"},{"id":"2507.15337","title":"Reasoning Models are Test Exploiters: Rethinking Multiple-Choice","created":"2025-07-21","cited_by_count":11,"area":"lr"},{"id":"2503.10573","title":"Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach","created":"2025-03-13","cited_by_count":8,"area":"lr"},{"id":"2603.22582","title":"Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2507.17307","title":"R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning","created":"2025-07-23","cited_by_count":7,"area":"lr"},{"id":"2509.08814","title":"Merge-of-Thought Distillation","created":"2025-09-10","cited_by_count":7,"area":"lr"},{"id":"2509.25426","title":"RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2502.11684","title":"MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task","created":"2025-02-17","cited_by_count":5,"area":"lr"},{"id":"2512.07019","title":"Latency-Response Theory Model: Evaluating Large Language Models via Response Accuracy and Chain-of-Thought Length","created":"2025-12-07","cited_by_count":5,"area":"lr"},{"id":"2605.10075","title":"Active Testing of Large Language Models via Approximate Neyman Allocation","created":"2026-05-11","cited_by_count":5,"area":"lr"},{"id":"2412.01621","title":"NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers","created":"2024-12-02","cited_by_count":4,"area":"lr"},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2510.21007","title":"Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2605.11467","title":"Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2511.01866","title":"EdgeReasoning: Characterizing Reasoning LLM Deployment on Edge GPUs","created":"2025-10-21","cited_by_count":1,"area":"lr"},{"id":"2602.02550","title":"HyPAC: Cost-Efficient LLMs-Human Hybrid Annotation with PAC Error Guarantees","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2603.09556","title":"ALARM: Audio-Language Alignment for Reasoning Models","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2605.02442","title":"Measuring AI Reasoning: A Guide for Researchers","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2608.22854","title":"Thinking at the Right Size: Amortized Distillation Across Post-Trained LLMs","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.17686","title":"The Missing \"I Don't Know\": Why Three Reasoning-Reliability Findings Converge on Calibrated Abstention","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2610.03509","title":"Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.17456","title":"Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}