{"total":29,"rows":[{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106,"area":"lr"},{"id":"2512.07783","title":"On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models","created":"2025-12-08","cited_by_count":69,"area":"lr"},{"id":"2508.01191","title":"Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens","created":"2025-08-02","cited_by_count":43,"area":"lr"},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2511.00330","title":"Sherlock: Reliable and Efficient Agentic Workflow Execution","created":"2025-11-01","cited_by_count":11,"area":"lr"},{"id":"2510.01539","title":"Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2510.08325","title":"Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries","created":"2025-10-09","cited_by_count":9,"area":"lr"},{"id":"2510.10494","title":"Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning","created":"2025-10-12","cited_by_count":9,"area":"lr"},{"id":"2512.24063","title":"How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns","created":"2025-12-30","cited_by_count":8,"area":"lr"},{"id":"2510.13903","title":"Benefits and Limitations of Communication in Multi-Agent Reasoning","created":"2025-10-14","cited_by_count":7,"area":"lr"},{"id":"2512.01775","title":"How Does RL Post-training Induce Skill Composition? A Case Study on Countdown","created":"2025-12-01","cited_by_count":6,"area":"lr"},{"id":"2510.25528","title":"Zero Reinforcement Learning Towards General Domains","created":"2025-10-29","cited_by_count":5,"area":"lr"},{"id":"2510.03605","title":"Understanding the Role of Training Data in Test-Time Scaling","created":"2025-10-04","cited_by_count":4,"area":"lr"},{"id":"2511.14777","title":"The Illusion of Procedural Reasoning: Measuring Long-Horizon FSM Execution in LLMs","created":"2025-11-05","cited_by_count":3,"area":"lr"},{"id":"2507.01231","title":"Rethinking the Illusion of Thinking","created":"2025-07-01","cited_by_count":2,"area":"lr"},{"id":"2510.06274","title":"Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization","created":"2025-10-06","cited_by_count":1,"area":"lr"},{"id":"2512.20812","title":"Semantic Deception: When Reasoning Models Can't Compute an Addition","created":"2025-12-23","cited_by_count":1,"area":"lr"},{"id":"2601.21214","title":"Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2508.10173","title":"Benchmark-Driven Selection of AI: Evidence from DeepSeek-R1","created":"2025-08-13","cited_by_count":0,"area":"lr"},{"id":"2509.21998","title":"GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2602.00927","title":"Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2604.03374","title":"CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2605.29190","title":"When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.06526","title":"CrowdMath: A Dataset of Crowdsourced Mathematical Research Discussions","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2607.05992","title":"PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.00331","title":"Mathematical Transfer in LLMs Follows Reasoning Approach More Than Topic","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.04158","title":"How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}