{"total":52,"rows":[{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427,"area":"lr"},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110,"area":"lr"},{"id":"2402.01620","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","created":"2024-02-02","cited_by_count":43,"area":"lr"},{"id":"2410.09918","title":"Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces","created":"2024-10-13","cited_by_count":43,"area":"lr"},{"id":"2308.08614","title":"Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought","created":"2023-08-16","cited_by_count":41,"area":"lr"},{"id":"2502.18001","title":"Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning","created":"2025-02-25","cited_by_count":40,"area":"lr"},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2502.01694","title":"Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation","created":"2025-02-02","cited_by_count":25,"area":"lr"},{"id":"2505.14582","title":"Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning","created":"2025-05-20","cited_by_count":19,"area":"lr"},{"id":"2309.13075","title":"SCREWS: A Modular Framework for Reasoning with Revisions","created":"2023-09-20","cited_by_count":16,"area":"lr"},{"id":"2406.14511","title":"Investigating Mysteries of CoT-Augmented Distillation","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2405.19737","title":"Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation","created":"2024-05-30","cited_by_count":14,"area":"lr"},{"id":"2410.03663","title":"Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review","created":"2024-10-04","cited_by_count":14,"area":"lr"},{"id":"2310.13332","title":"Democratizing Reasoning Ability: Tailored Learning from Large Language Model","created":"2023-10-20","cited_by_count":13,"area":"lr"},{"id":"2404.09170","title":"Distilling Reasoning Ability from Large Language Models with Adaptive Thinking","created":"2024-04-14","cited_by_count":13,"area":"lr"},{"id":"2502.19557","title":"Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?","created":"2025-02-26","cited_by_count":12,"area":"lr"},{"id":"2501.08248","title":"Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models","created":"2025-01-14","cited_by_count":11,"area":"lr"},{"id":"2508.16695","title":"Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?","created":"2025-08-21","cited_by_count":11,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2506.03541","title":"Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement","created":"2025-06-04","cited_by_count":10,"area":"lr"},{"id":"2506.04611","title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","created":"2025-06-05","cited_by_count":9,"area":"lr"},{"id":"2403.14312","title":"ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting","created":"2024-03-21","cited_by_count":8,"area":"lr"},{"id":"2505.13792","title":"Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2506.03616","title":"Learning to Insert [PAUSE] Tokens for Better Reasoning","created":"2025-06-04","cited_by_count":8,"area":"lr"},{"id":"2504.09802","title":"Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment","created":"2025-04-14","cited_by_count":7,"area":"lr"},{"id":"2509.21282","title":"It's Not You, It's Clipping: A Soft Trust-Region via Probability Smoothing for LLM RL","created":"2025-09-25","cited_by_count":7,"area":"lr"},{"id":"2606.01476","title":"OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification","created":"2026-05-31","cited_by_count":7,"area":"lr"},{"id":"2410.18574","title":"SIKeD: Self-guided Iterative Knowledge Distillation for mathematical reasoning","created":"2024-10-24","cited_by_count":6,"area":"lr"},{"id":"2501.09804","title":"Enhancing Generalization in Chain of Thought Reasoning for Smaller Models","created":"2025-01-16","cited_by_count":5,"area":"lr"},{"id":"2502.16806","title":"CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers","created":"2025-02-24","cited_by_count":4,"area":"lr"},{"id":"2506.07751","title":"AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2511.05528","title":"SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2402.01812","title":"Distilling LLMs' Decomposition Abilities into Compact Language Models","created":"2024-02-02","cited_by_count":3,"area":"lr"},{"id":"2405.13004","title":"MathDivide: Improved mathematical reasoning by large language models","created":"2024-05-12","cited_by_count":3,"area":"lr"},{"id":"2503.11336","title":"Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models","created":"2025-03-14","cited_by_count":3,"area":"lr"},{"id":"2504.20946","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","created":"2025-04-29","cited_by_count":3,"area":"lr"},{"id":"2401.06930","title":"PizzaCommonSense: Learning to Model Commonsense Reasoning about Intermediate Steps in Cooking Recipes","created":"2024-01-12","cited_by_count":2,"area":"lr"},{"id":"2505.11628","title":"Critique-Guided Distillation for Robust Reasoning via Refinement","created":"2025-05-16","cited_by_count":2,"area":"lr"},{"id":"2602.14469","title":"Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2606.22938","title":"Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently","created":"2026-06-22","cited_by_count":2,"area":"lr"},{"id":"2212.09721","title":"KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales","created":"2022-12-19","cited_by_count":1,"area":"lr"},{"id":"2308.04711","title":"Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense Retrieval","created":"2023-08-09","cited_by_count":1,"area":"lr"},{"id":"2402.03667","title":"Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning","created":"2024-02-06","cited_by_count":1,"area":"lr"},{"id":"2403.01969","title":"AS-ES Learning: Towards Efficient CoT Learning in Small Models","created":"2024-03-04","cited_by_count":1,"area":"lr"},{"id":"2410.16924","title":"SleepCoT: A Lightweight Personalized Sleep Health Model via Chain-of-Thought Distillation","created":"2024-10-22","cited_by_count":1,"area":"lr"},{"id":"2508.05496","title":"InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2605.04078","title":"Validity-Calibrated Reasoning Distillation","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2512.08480","title":"Soft Inductive Bias Approach via Explicit Reasoning Perspectives in Inappropriate Utterance Detection Using Large Language Models","created":"2025-12-09","cited_by_count":0,"area":"lr"},{"id":"2605.07139","title":"Structural Rationale Distillation via Reasoning Space Compression","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.08094","title":"MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning Correction","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2610.12933","title":"Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}