{"total":93,"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":"2309.13007","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","created":"2023-09-22","cited_by_count":309,"area":"lr"},{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295,"area":"lr"},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282,"area":"lr"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"id":"2305.18323","title":"ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models","created":"2023-05-23","cited_by_count":184,"area":"lr"},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177,"area":"lr"},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117,"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":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108,"area":"lr"},{"id":"2401.10480","title":"Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning","created":"2024-01-19","cited_by_count":108,"area":"lr"},{"id":"2401.08190","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","created":"2024-01-16","cited_by_count":81,"area":"lr"},{"id":"2305.18395","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","created":"2023-05-28","cited_by_count":64,"area":"lr"},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"area":"lr"},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"area":"lr"},{"id":"2408.13457","title":"Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning","created":"2024-08-24","cited_by_count":63,"area":"lr"},{"id":"2310.04959","title":"Towards Better Chain-of-Thought Prompting Strategies: A Survey","created":"2023-10-08","cited_by_count":62,"area":"lr"},{"id":"2305.03453","title":"T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering","created":"2023-05-05","cited_by_count":60,"area":"lr"},{"id":"2411.18478","title":"Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS","created":"2024-11-27","cited_by_count":54,"area":"lr"},{"id":"2402.04616","title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","created":"2024-02-07","cited_by_count":47,"area":"lr"},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"id":"2305.05181","title":"MoT: Memory-of-Thought Enables ChatGPT to Self-Improve","created":"2023-05-09","cited_by_count":38,"area":"lr"},{"id":"2305.14934","title":"GRACE: Discriminator-Guided Chain-of-Thought Reasoning","created":"2023-05-24","cited_by_count":35,"area":"lr"},{"id":"2305.12147","title":"LogiCoT: Logical Chain-of-Thought Instruction-Tuning","created":"2023-05-20","cited_by_count":31,"area":"lr"},{"id":"2404.10346","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","created":"2024-04-16","cited_by_count":31,"area":"lr"},{"id":"2305.13888","title":"PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning","created":"2023-05-23","cited_by_count":29,"area":"lr"},{"id":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29,"area":"lr"},{"id":"2503.15848","title":"Entropy-based Exploration Conduction for Multi-step Reasoning","created":"2025-03-20","cited_by_count":29,"area":"lr"},{"id":"2310.14747","title":"MCC-KD: Multi-CoT Consistent Knowledge Distillation","created":"2023-10-23","cited_by_count":28,"area":"lr"},{"id":"2312.05562","title":"Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models","created":"2023-12-09","cited_by_count":27,"area":"lr"},{"id":"2412.08972","title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","created":"2024-12-12","cited_by_count":27,"area":"lr"},{"id":"2309.13182","title":"Effective Distillation of Table-based Reasoning Ability from LLMs","created":"2023-09-22","cited_by_count":23,"area":"lr"},{"id":"2405.07551","title":"MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning","created":"2024-05-13","cited_by_count":22,"area":"lr"},{"id":"2305.01505","title":"Beyond Classification: Financial Reasoning in State-of-the-Art Language Models","created":"2023-04-30","cited_by_count":19,"area":"lr"},{"id":"2308.15452","title":"When Do Program-of-Thoughts Work for Reasoning?","created":"2023-08-29","cited_by_count":19,"area":"lr"},{"id":"2312.10730","title":"Mixed Distillation Helps Smaller Language Model Better Reasoning","created":"2023-12-17","cited_by_count":19,"area":"lr"},{"id":"2401.13223","title":"TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data","created":"2024-01-24","cited_by_count":19,"area":"lr"},{"id":"2409.01281","title":"Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs","created":"2024-08-25","cited_by_count":17,"area":"lr"},{"id":"2307.07951","title":"MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning","created":"2023-07-16","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":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15,"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":"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":"2503.01461","title":"Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models","created":"2025-03-03","cited_by_count":13,"area":"lr"},{"id":"2303.15714","title":"Explicit Planning Helps Language Models in Logical Reasoning","created":"2023-03-28","cited_by_count":12,"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":"2601.21968","title":"OVD: On-policy Verbal Distillation","created":"2026-01-29","cited_by_count":11,"area":"lr"},{"id":"2605.12483","title":"Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training","created":"2026-05-12","cited_by_count":11,"area":"lr"},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2404.12728","title":"Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?","created":"2024-04-19","cited_by_count":8,"area":"lr"},{"id":"2408.12337","title":"Fine-tuning Smaller Language Models for Question Answering over Financial Documents","created":"2024-08-22","cited_by_count":8,"area":"lr"},{"id":"2509.23574","title":"Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2310.04743","title":"Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models","created":"2023-10-07","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":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2310.05074","title":"DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models","created":"2023-10-08","cited_by_count":6,"area":"lr"},{"id":"2509.05602","title":"Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation","created":"2025-09-06","cited_by_count":6,"area":"lr"},{"id":"2410.22597","title":"Are Large-Language Models Graph Algorithmic Reasoners?","created":"2024-10-29","cited_by_count":5,"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":"2503.23913","title":"Entropy-Based Adaptive Weighting for Self-Training","created":"2025-03-31","cited_by_count":5,"area":"lr"},{"id":"2504.05632","title":"Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning","created":"2025-04-08","cited_by_count":5,"area":"lr"},{"id":"2311.06985","title":"Large Language Models are In-context Teachers for Knowledge Reasoning","created":"2023-11-12","cited_by_count":4,"area":"lr"},{"id":"2502.15335","title":"Stepwise Informativeness Search for Efficient and Effective LLM Reasoning","created":"2025-02-21","cited_by_count":4,"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":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2410.12568","title":"Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving","created":"2024-10-16","cited_by_count":3,"area":"lr"},{"id":"2505.18831","title":"Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning","created":"2025-05-24","cited_by_count":3,"area":"lr"},{"id":"2510.09351","title":"ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2602.21103","title":"Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning","created":"2026-02-24","cited_by_count":3,"area":"lr"},{"id":"2412.05967","title":"Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its prompt","created":"2024-12-08","cited_by_count":2,"area":"lr"},{"id":"2504.15188","title":"Synergistic Weak-Strong Collaboration by Aligning Preferences","created":"2025-04-21","cited_by_count":2,"area":"lr"},{"id":"2511.08024","title":"Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning","created":"2025-11-11","cited_by_count":2,"area":"lr"},{"id":"2602.05307","title":"MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language Models","created":"2026-02-05","cited_by_count":2,"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":"2404.03891","title":"Can only LLMs do Reasoning?: Potential of Small Language Models in Task Planning","created":"2024-04-05","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":"2507.19749","title":"Can LLMs Solve ASP Problems? Insights from a Benchmarking Study (Extended Version)","created":"2025-07-26","cited_by_count":1,"area":"lr"},{"id":"2603.19266","title":"Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion","created":"2026-02-26","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":"2605.26038","title":"DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models","created":"2026-05-25","cited_by_count":1,"area":"lr"},{"id":"2510.16686","title":"Investigating the Impact of Rationales for LLMs on Natural Language Understanding","created":"2025-10-19","cited_by_count":0,"area":"lr"},{"id":"2511.12368","title":"Fast Reasoning Segmentation for Images and Videos","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2602.21061","title":"Tool Use Reduces Depth-Induced Collapse in OOD Reasoning","created":"2026-02-24","cited_by_count":0,"area":"lr"},{"id":"2604.19488","title":"CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2608.14685","title":"Rethinking Reverse KL as Adaptive Entropy Distillation","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2609.13770","title":"Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation","created":"2026-09-12","cited_by_count":0,"area":"lr"},{"id":"2609.25643","title":"Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2610.09587","title":"Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.19741","title":"Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}