{"total":147,"rows":[{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752,"area":"lr"},{"id":"2412.21187","title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","created":"2024-12-30","cited_by_count":570,"area":"lr"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"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":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"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":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251,"area":"lr"},{"id":"2412.18547","title":"Token-Budget-Aware LLM Reasoning","created":"2024-12-24","cited_by_count":247,"area":"lr"},{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225,"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":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148,"area":"lr"},{"id":"2310.16436","title":"DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models","created":"2023-10-25","cited_by_count":128,"area":"lr"},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2401.06853","title":"Large Language Models Can Learn Temporal Reasoning","created":"2024-01-12","cited_by_count":111,"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":"2310.20689","title":"Learning From Mistakes Makes LLM Better Reasoner","created":"2023-10-31","cited_by_count":101,"area":"lr"},{"id":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"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":"2411.16646","title":"Self-Generated Critiques Boost Reward Modeling for Language Models","created":"2024-11-25","cited_by_count":71,"area":"lr"},{"id":"2405.13872","title":"Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models","created":"2024-05-22","cited_by_count":65,"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":"2310.04959","title":"Towards Better Chain-of-Thought Prompting Strategies: A Survey","created":"2023-10-08","cited_by_count":62,"area":"lr"},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"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":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51,"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":"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":"2401.07037","title":"xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning","created":"2024-01-13","cited_by_count":46,"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":"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":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2404.16033","title":"Cantor: Inspiring Multimodal Chain-of-Thought of MLLM","created":"2024-04-24","cited_by_count":34,"area":"lr"},{"id":"2404.14963","title":"Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems","created":"2024-04-23","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":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","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":"2308.06207","title":"Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals","created":"2023-08-11","cited_by_count":24,"area":"lr"},{"id":"2502.12466","title":"EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking","created":"2025-02-18","cited_by_count":24,"area":"lr"},{"id":"2503.05641","title":"Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills","created":"2025-03-07","cited_by_count":24,"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":"2311.08206","title":"Human-Centric Autonomous Systems With LLMs for User Command Reasoning","created":"2023-11-14","cited_by_count":22,"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":"2505.15817","title":"Learning to Reason via Mixture-of-Thought for Logical Reasoning","created":"2025-05-21","cited_by_count":20,"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":"2505.22457","title":"Fostering Video Reasoning via Next-Event Prediction","created":"2025-05-28","cited_by_count":18,"area":"lr"},{"id":"2403.13271","title":"Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs","created":"2024-03-20","cited_by_count":17,"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":"2308.01906","title":"Reasoning in Large Language Models Through Symbolic Math Word Problems","created":"2023-08-03","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":"2310.19019","title":"TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise","created":"2023-10-29","cited_by_count":15,"area":"lr"},{"id":"2312.05434","title":"Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models","created":"2023-12-09","cited_by_count":15,"area":"lr"},{"id":"2505.19716","title":"Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting","created":"2025-05-26","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":"2412.18292","title":"Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration","created":"2024-12-24","cited_by_count":14,"area":"lr"},{"id":"2511.07378","title":"Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization","created":"2025-11-10","cited_by_count":14,"area":"lr"},{"id":"2308.04679","title":"Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA","created":"2023-08-09","cited_by_count":13,"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":"2407.03181","title":"Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs","created":"2024-07-03","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":"2306.17820","title":"Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models","created":"2023-06-30","cited_by_count":11,"area":"lr"},{"id":"2310.06692","title":"Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models","created":"2023-10-10","cited_by_count":11,"area":"lr"},{"id":"2402.16844","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","created":"2024-02-26","cited_by_count":11,"area":"lr"},{"id":"2510.22728","title":"S-Chain: Structured Visual Chain-of-Thought For Medicine","created":"2025-10-26","cited_by_count":11,"area":"lr"},{"id":"2601.21968","title":"OVD: On-policy Verbal Distillation","created":"2026-01-29","cited_by_count":11,"area":"lr"},{"id":"2403.19167","title":"Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering","created":"2024-03-28","cited_by_count":10,"area":"lr"},{"id":"2502.04667","title":"Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning","created":"2025-02-07","cited_by_count":10,"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":"2407.02340","title":"RVISA: Reasoning and Verification for Implicit Sentiment Analysis","created":"2024-07-02","cited_by_count":9,"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":"2402.15420","title":"PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning","created":"2024-02-23","cited_by_count":8,"area":"lr"},{"id":"2403.09085","title":"Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance","created":"2024-03-14","cited_by_count":8,"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":"2405.09848","title":"Enhancing Semantics in Multimodal Chain of Thought via Soft Negative Sampling","created":"2024-05-16","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":"2506.03616","title":"Learning to Insert [PAUSE] Tokens for Better Reasoning","created":"2025-06-04","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":"2605.19433","title":"Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2306.13899","title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","created":"2023-06-24","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":"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":"2401.13849","title":"TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance","created":"2024-01-24","cited_by_count":6,"area":"lr"},{"id":"2406.07393","title":"Large Language Models are Limited in Out-of-Context Knowledge Reasoning","created":"2024-06-11","cited_by_count":6,"area":"lr"},{"id":"2406.16061","title":"PORT: Preference Optimization on Reasoning Traces","created":"2024-06-23","cited_by_count":6,"area":"lr"},{"id":"2505.15927","title":"CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision","created":"2025-05-21","cited_by_count":6,"area":"lr"},{"id":"2505.16322","title":"AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners","created":"2025-05-22","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":"2412.01663","title":"DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline","created":"2024-12-02","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":"2510.18863","title":"EffiReasonTrans: RL-Optimized Reasoning for Code Translation","created":"2025-10-21","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":"2411.07611","title":"Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models","created":"2024-11-12","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"}],"next_cursor":"100"}