{"total":30,"rows":[{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433,"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":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113,"area":"lr"},{"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":"2405.12205","title":"Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving","created":"2024-05-20","cited_by_count":84,"area":"lr"},{"id":"2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","created":"2024-05-23","cited_by_count":79,"area":"lr"},{"id":"2410.16033","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","created":"2024-10-18","cited_by_count":61,"area":"lr"},{"id":"2506.02867","title":"Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning","created":"2025-06-03","cited_by_count":51,"area":"lr"},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44,"area":"lr"},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2501.11877","title":"From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning","created":"2025-01-21","cited_by_count":12,"area":"lr"},{"id":"2505.15110","title":"RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals","created":"2025-05-21","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":"2506.06998","title":"What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2404.10975","title":"Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models","created":"2024-04-17","cited_by_count":4,"area":"lr"},{"id":"2410.17088","title":"Science Out of Its Ivory Tower: Improving Accessibility with Reinforcement Learning","created":"2024-10-22","cited_by_count":3,"area":"lr"},{"id":"2510.26519","title":"Think Outside the Policy: In-Context Steered Policy Optimization","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2602.02545","title":"Beyond Alignment: Expanding Reasoning Capacity via Manifold-Reshaping Policy Optimization","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2404.15206","title":"Does Instruction Tuning Make LLMs More Consistent?","created":"2024-04-23","cited_by_count":2,"area":"lr"},{"id":"2508.21378","title":"RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation","created":"2025-08-29","cited_by_count":2,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2507.06999","title":"Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMs","created":"2025-07-09","cited_by_count":1,"area":"lr"},{"id":"2511.10707","title":"Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2511.12155","title":"Rethinking Deep Alignment Through The Lens Of Incomplete Learning","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2511.21214","title":"Self-Guided Adaptive Safety Alignment: Synthesizing and Internalizing Guidelines in Reasoning Models","created":"2025-11-26","cited_by_count":0,"area":"lr"},{"id":"2602.01561","title":"Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.06650","title":"Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2607.00531","title":"Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2610.04751","title":"Dynamic Routing as a New Dimension for Test-time Versatility of LLMs","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.14270","title":"The Thinking Leakage in Reinforcement Learning for LLMs","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}