{"total":171,"rows":[{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551,"area":"lr"},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454,"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":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"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":"2401.04398","title":"Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding","created":"2024-01-09","cited_by_count":188,"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":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"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":"2501.05707","title":"Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains","created":"2025-01-10","cited_by_count":95,"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":"2504.20595","title":"ReasonIR: Training Retrievers for Reasoning Tasks","created":"2025-04-29","cited_by_count":77,"area":"lr"},{"id":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2411.00855","title":"Vision-Language Models Can Self-Improve Reasoning via Reflection","created":"2024-10-30","cited_by_count":69,"area":"lr"},{"id":"2312.03052","title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","created":"2023-12-05","cited_by_count":66,"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":"2309.02144","title":"Making Large Language Models Better Reasoners with Alignment","created":"2023-09-05","cited_by_count":63,"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":"2404.15676","title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","created":"2024-04-24","cited_by_count":48,"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":"2604.10688","title":"SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting","created":"2026-04-12","cited_by_count":43,"area":"lr"},{"id":"2505.13775","title":"Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens","created":"2025-05-19","cited_by_count":41,"area":"lr"},{"id":"2410.04509","title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","created":"2024-10-06","cited_by_count":37,"area":"lr"},{"id":"2504.09762","title":"Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!","created":"2025-04-14","cited_by_count":37,"area":"lr"},{"id":"2305.14934","title":"GRACE: Discriminator-Guided Chain-of-Thought Reasoning","created":"2023-05-24","cited_by_count":35,"area":"lr"},{"id":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2312.07399","title":"Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales","created":"2023-12-12","cited_by_count":33,"area":"lr"},{"id":"2305.12147","title":"LogiCoT: Logical Chain-of-Thought Instruction-Tuning","created":"2023-05-20","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":"2403.04260","title":"Can Small Language Models be Good Reasoners for Sequential Recommendation?","created":"2024-03-07","cited_by_count":26,"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":"2309.13182","title":"Effective Distillation of Table-based Reasoning Ability from LLMs","created":"2023-09-22","cited_by_count":23,"area":"lr"},{"id":"2412.01282","title":"Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement","created":"2024-12-02","cited_by_count":23,"area":"lr"},{"id":"2403.12596","title":"Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs","created":"2024-03-19","cited_by_count":20,"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":"2403.16385","title":"Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","created":"2024-03-25","cited_by_count":19,"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":"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":"2606.18974","title":"Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning","created":"2026-06-17","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":"2506.08817","title":"Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought","created":"2025-06-10","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":"2402.16631","title":"GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning","created":"2024-02-26","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":"2412.03409","title":"PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation","created":"2024-12-04","cited_by_count":13,"area":"lr"},{"id":"2310.01446","title":"Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning","created":"2023-10-01","cited_by_count":12,"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":"2508.16861","title":"Learning from Diverse Reasoning Paths with Routing and Collaboration","created":"2025-08-23","cited_by_count":12,"area":"lr"},{"id":"2509.09284","title":"Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning","created":"2025-09-11","cited_by_count":12,"area":"lr"},{"id":"2311.13063","title":"From Classification to Clinical Insights: Towards Analyzing and Reasoning About Mobile and Behavioral Health Data With Large Language Models","created":"2023-11-21","cited_by_count":11,"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":"2503.24198","title":"TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance","created":"2025-03-31","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":"2504.06606","title":"Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program","created":"2025-04-09","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":"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":"2509.07339","title":"Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity","created":"2025-09-09","cited_by_count":9,"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":"2505.12768","title":"ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL","created":"2025-05-19","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":"2606.29340","title":"PHF: Privileged Hidden Flow for On-Policy Self-Distillation","created":"2026-06-28","cited_by_count":8,"area":"lr"},{"id":"2503.09620","title":"Exploiting Edited Large Language Models as General Scientific Optimizers","created":"2025-03-08","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":"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":"2407.19405","title":"Logic Distillation: Learning from Code Function by Function for Decision-making Tasks","created":"2024-07-28","cited_by_count":5,"area":"lr"},{"id":"2409.13203","title":"Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks","created":"2024-09-20","cited_by_count":5,"area":"lr"},{"id":"2608.11829","title":"Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling","created":"2026-08-12","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":"2405.03821","title":"Thoughtful Things: Building Human-Centric Smart Devices with Small Language Models","created":"2024-05-06","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":"2506.06470","title":"SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2507.02804","title":"Multimodal Mathematical Reasoning with Diverse Solving Perspective","created":"2025-07-03","cited_by_count":4,"area":"lr"},{"id":"2509.05226","title":"Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation","created":"2025-09-05","cited_by_count":4,"area":"lr"},{"id":"2509.18316","title":"Brittleness and Promise: Knowledge Graph Based Reward Modeling for Diagnostic Reasoning","created":"2025-09-22","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":"2510.18982","title":"Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality","created":"2025-10-21","cited_by_count":4,"area":"lr"},{"id":"2605.21127","title":"Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning","created":"2026-05-20","cited_by_count":4,"area":"lr"},{"id":"2606.09887","title":"SocraticPO: Policy Optimization via Interactive Guidance","created":"2026-06-03","cited_by_count":4,"area":"lr"},{"id":"2309.10444","title":"Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models","created":"2023-09-19","cited_by_count":3,"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":"2406.11375","title":"Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?","created":"2024-06-17","cited_by_count":3,"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":"2502.12744","title":"Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation","created":"2025-02-18","cited_by_count":3,"area":"lr"},{"id":"2506.09396","title":"Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models","created":"2025-06-11","cited_by_count":3,"area":"lr"},{"id":"2507.05707","title":"Agentic-R1: Distilled Dual-Strategy Reasoning","created":"2025-07-08","cited_by_count":3,"area":"lr"},{"id":"2509.22921","title":"Rethinking Large Language Model Distillation: A Constrained Markov Decision Process Perspective","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2511.05747","title":"CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization","created":"2025-11-07","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":"2605.08625","title":"Reasoning-Aware Training for Time Series Forecasting","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2609.28145","title":"RL Starts before RL: On Policy Distillation for Better Reinforcement Learning","created":"2026-09-23","cited_by_count":3,"area":"lr"},{"id":"2310.08420","title":"Visual Attention Prompted Prediction and Learning","created":"2023-10-12","cited_by_count":2,"area":"lr"},{"id":"2401.04319","title":"Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs","created":"2024-01-09","cited_by_count":2,"area":"lr"},{"id":"2406.12269","title":"Unveiling Implicit Table Knowledge with Question-Then-Pinpoint Reasoner for Insightful Table Summarization","created":"2024-06-18","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}