{"total":26,"rows":[{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2403.04706","title":"Common 7B Language Models Already Possess Strong Math Capabilities","created":"2024-03-07","cited_by_count":109,"area":"lr"},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2502.13260","title":"Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models","created":"2025-02-18","cited_by_count":51,"area":"lr"},{"id":"2407.13647","title":"Weak-to-Strong Reasoning","created":"2024-07-18","cited_by_count":33,"area":"lr"},{"id":"2406.13948","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"id":"2510.01982","title":"Fine-Grained GRPO for Precise Preference Alignment in Flow Models","created":"2025-10-02","cited_by_count":21,"area":"lr"},{"id":"2506.23219","title":"UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding","created":"2025-06-29","cited_by_count":15,"area":"lr"},{"id":"2404.01067","title":"Exploring the Mystery of Influential Data for Mathematical Reasoning","created":"2024-04-01","cited_by_count":13,"area":"lr"},{"id":"2502.15401","title":"Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning","created":"2025-02-21","cited_by_count":12,"area":"lr"},{"id":"2506.02096","title":"SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis","created":"2025-06-02","cited_by_count":12,"area":"lr"},{"id":"2410.02229","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning","created":"2024-10-03","cited_by_count":10,"area":"lr"},{"id":"2507.14783","title":"Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling","created":"2025-07-20","cited_by_count":10,"area":"lr"},{"id":"2502.02988","title":"Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons","created":"2025-02-05","cited_by_count":9,"area":"lr"},{"id":"2506.19469","title":"Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement Learning","created":"2025-06-24","cited_by_count":5,"area":"lr"},{"id":"2407.14562","title":"Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thought","created":"2024-07-18","cited_by_count":4,"area":"lr"},{"id":"2507.03051","title":"Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization","created":"2025-07-03","cited_by_count":4,"area":"lr"},{"id":"2509.00425","title":"The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang","created":"2025-08-30","cited_by_count":3,"area":"lr"},{"id":"2502.11901","title":"Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2510.20519","title":"Metis-HOME: Hybrid Optimized Mixture-of-Experts for Multimodal Reasoning","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2404.03887","title":"SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models","created":"2024-04-05","cited_by_count":0,"area":"lr"},{"id":"2511.08172","title":"An Efficient Training Pipeline for Reasoning Graphical User Interface Agents","created":"2025-11-11","cited_by_count":0,"area":"lr"},{"id":"2512.08169","title":"Information-Dense Reasoning for Efficient and Auditable Security Alert Triage","created":"2025-12-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}