{"total":83,"rows":[{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711,"area":null},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"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":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2502.13842","title":"Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking","created":"2025-02-19","cited_by_count":57,"area":"lr"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"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":"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":"2604.01193","title":"Embarrassingly Simple Self-Distillation Improves Code Generation","created":"2026-04-01","cited_by_count":40,"area":"distill"},{"id":"2503.15888","title":"Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models","created":"2025-03-20","cited_by_count":39,"area":"rag"},{"id":"2510.09285","title":"Spotlight on Token Perception for Multimodal Reinforcement Learning","created":"2025-10-10","cited_by_count":39,"area":"lr"},{"id":"2607.05184","title":"Rethinking On-Policy Self-Distillation for Thinking Models","created":"2026-07-06","cited_by_count":39,"area":"lr"},{"id":"2509.19803","title":"VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models","created":"2025-09-24","cited_by_count":36,"area":"lr"},{"id":"2505.24718","title":"Reinforcing Video Reasoning with Focused Thinking","created":"2025-05-30","cited_by_count":31,"area":"lr"},{"id":"2502.00290","title":"Estimating LLM Uncertainty with Evidence","created":"2025-02-01","cited_by_count":26,"area":null},{"id":"2606.22600","title":"On the Position Bias of On-Policy Distillation","created":"2026-06-21","cited_by_count":26,"area":"lr"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2506.09996","title":"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring","created":"2025-06-11","cited_by_count":22,"area":"alignment"},{"id":"2603.22446","title":"Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs","created":"2026-03-23","cited_by_count":20,"area":"lr"},{"id":"2505.17312","title":"AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models","created":"2025-05-22","cited_by_count":17,"area":"lr"},{"id":"2509.22485","title":"Group Critical-token Policy Optimization for Autoregressive Image Generation","created":"2025-09-26","cited_by_count":17,"area":null},{"id":"2605.10194","title":"STEPS: Selective On-Policy Self-Distillation for Reasoning","created":"2026-05-11","cited_by_count":16,"area":"distill"},{"id":"2502.11475","title":"Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points","created":"2025-02-17","cited_by_count":14,"area":"lr"},{"id":"2505.19653","title":"Token-Importance Guided Direct Preference Optimization","created":"2025-05-26","cited_by_count":14,"area":"alignment"},{"id":"2503.17363","title":"Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique","created":"2025-03-21","cited_by_count":13,"area":"lr"},{"id":"2506.07851","title":"Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning","created":"2025-06-09","cited_by_count":13,"area":"inference"},{"id":"2508.00574","title":"SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought","created":"2025-08-01","cited_by_count":13,"area":"lr"},{"id":"2412.20372","title":"LLM2: Let Large Language Models Harness System 2 Reasoning","created":"2024-12-29","cited_by_count":12,"area":"lr"},{"id":"2506.14907","title":"PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning","created":"2025-06-17","cited_by_count":11,"area":"lr"},{"id":"2503.02783","title":"Teaching Your Models to Understand Code via Focal Preference Alignment","created":"2025-03-04","cited_by_count":10,"area":"alignment"},{"id":"2512.00908","title":"Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs","created":"2025-11-30","cited_by_count":10,"area":"lr"},{"id":"2502.16706","title":"DISC: Dynamic Decomposition Improves LLM Inference Scaling","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2511.06190","title":"Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning","created":"2025-11-09","cited_by_count":9,"area":"lr"},{"id":"2605.07260","title":"When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models","created":"2026-05-08","cited_by_count":9,"area":"moe"},{"id":"2601.05167","title":"RelayLLM: Efficient Reasoning via Collaborative Decoding","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2601.10245","title":"TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks","created":"2026-01-15","cited_by_count":8,"area":"lr"},{"id":"2602.11455","title":"Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning","created":"2026-02-12","cited_by_count":6,"area":"lr"},{"id":"2506.15710","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2601.04537","title":"Linear Dynamics in the RLVR Training of Large Language Models","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2601.10348","title":"Training-Trajectory-Aware Token Selection","created":"2026-01-15","cited_by_count":4,"area":"lr"},{"id":"2510.02919","title":"Self-Reflective Generation at Test Time","created":"2025-10-03","cited_by_count":3,"area":"lr"},{"id":"2510.07962","title":"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?","created":"2025-10-09","cited_by_count":3,"area":"lr"},{"id":"2602.23823","title":"APPO: Attention-guided Perception Policy Optimization for Video Reasoning","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2603.06595","title":"Rethinking Personalization in Large Language Models at the Token Level","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2603.09065","title":"Learning Adaptive LLM Decoding","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2604.26940","title":"Select to Think: Unlocking SLM Potential with Local Sufficiency","created":"2026-04-29","cited_by_count":3,"area":"lr"},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2504.11197","title":"Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance","created":"2025-04-15","cited_by_count":2,"area":"rag"},{"id":"2505.23540","title":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2602.11361","title":"Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verification","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2606.06188","title":"The Tell-Tale Norm: $\\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2505.23761","title":"Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2511.23136","title":"Multi-chain Graph Refinement and Selection for Reliable Reasoning in Large Language Models","created":"2025-11-28","cited_by_count":1,"area":"lr"},{"id":"2602.00425","title":"Segment-Level Attribution for Selective Learning of Long Reasoning Traces","created":"2026-01-31","cited_by_count":1,"area":"lr"},{"id":"2602.09533","title":"Autoregressive Direct Preference Optimization","created":"2026-02-10","cited_by_count":1,"area":"alignment"},{"id":"2604.20564","title":"Where Reasoning Breaks: Logic-Aware Path Selection by Controlling Logical Connectives in LLMs Reasoning Chains","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.08283","title":"HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.30789","title":"Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.08035","title":"DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning","created":"2026-06-06","cited_by_count":1,"area":"lr"},{"id":"2606.09926","title":"Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling","created":"2026-06-07","cited_by_count":1,"area":"lr"},{"id":"2606.12273","title":"Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models","created":"2026-06-10","cited_by_count":1,"area":"diffusion"},{"id":"2606.15621","title":"Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2606.18286","title":"CODEBLOCK: Learning to Supervise Code at the Right Granularity","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.19771","title":"Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning","created":"2026-06-18","cited_by_count":1,"area":"lr"},{"id":"2606.31484","title":"Fork-Think with Confidence","created":"2026-06-30","cited_by_count":1,"area":"lr"},{"id":"2608.24300","title":"Contrastive Branch Policy Optimization","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2510.10224","title":"Text2Token: Unsupervised Text Representation Learning with Token Target Prediction","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2510.11104","title":"Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization","created":"2025-10-13","cited_by_count":0,"area":"lr"},{"id":"2510.27462","title":"VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision","created":"2025-10-31","cited_by_count":0,"area":"lr"},{"id":"2601.19739","title":"TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.01227","title":"Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2604.16158","title":"AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.14457","title":"Stateful Reasoning via Insight Replay","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.21883","title":"Token-weighted Direct Preference Optimization with Attention","created":"2026-05-21","cited_by_count":0,"area":"alignment"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.03166","title":"KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.05185","title":"ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.23020","title":"Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality","created":"2026-08-24","cited_by_count":0,"area":"safety"},{"id":"2610.02491","title":"What Does a Token Cost? A Mixture-of-Agents Measurement of Sufficient Per-Token Compute","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.15412","title":"From Candidate Tokens to Final Outcomes: Decoding Relative Long-Horizon Candidate Value from Reasoning Model Representations","created":"2026-10-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}