{"total":21,"rows":[{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2502.19918","title":"Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":33,"area":"lr"},{"id":"2509.25300","title":"Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning","created":"2025-09-29","cited_by_count":29,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2505.13890","title":"Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2512.24574","title":"Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time","created":"2025-12-31","cited_by_count":10,"area":"lr"},{"id":"2503.15793","title":"DNR Bench: Benchmarking Over-Reasoning in Reasoning LLMs","created":"2025-03-20","cited_by_count":8,"area":"lr"},{"id":"2505.14552","title":"KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation","created":"2025-05-20","cited_by_count":7,"area":"lr"},{"id":"2512.20312","title":"TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning","created":"2025-12-23","cited_by_count":7,"area":"lr"},{"id":"2506.15787","title":"SLR: Automated Synthesis for Scalable Logical Reasoning","created":"2025-06-18","cited_by_count":6,"area":"lr"},{"id":"2511.22888","title":"Adversarial Training for Process Reward Models","created":"2025-11-28","cited_by_count":3,"area":"lr"},{"id":"2601.21937","title":"Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities","created":"2026-01-29","cited_by_count":2,"area":"lr"},{"id":"2603.02099","title":"Recursive Think-Answer Process for LLMs and VLMs","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2606.04579","title":"SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2506.00189","title":"Control-R: Towards controllable test-time scaling","created":"2025-05-30","cited_by_count":1,"area":"lr"},{"id":"2601.14696","title":"AdaTIR: Adaptive Tool-Integrated Reasoning via Difficulty-Aware Policy Optimization","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2507.23170","title":"BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning","created":"2025-07-31","cited_by_count":0,"area":"lr"},{"id":"2508.12277","title":"The Self-Execution Benchmark: Measuring LLMs' Attempts to Overcome Their Lack of Self-Execution","created":"2025-08-17","cited_by_count":0,"area":"lr"},{"id":"2509.06174","title":"From Long to Short: LLMs Excel at Trimming Own Reasoning Chains","created":"2025-09-07","cited_by_count":0,"area":"lr"},{"id":"2511.20680","title":"Cognitive bias in LLM reasoning compromises interpretation of clinical oncology notes","created":"2025-11-16","cited_by_count":0,"area":"lr"}],"next_cursor":null}