{"total":166,"rows":[{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228,"area":"lr"},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2506.20639","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","created":"2025-06-25","cited_by_count":187,"area":"diffusion"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2506.18254","title":"RLPR: Extrapolating RLVR to General Domains without Verifiers","created":"2025-06-23","cited_by_count":85,"area":"lr"},{"id":"2507.10532","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","created":"2025-07-14","cited_by_count":82,"area":"lr"},{"id":"2509.21880","title":"No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping","created":"2025-09-26","cited_by_count":50,"area":"lr"},{"id":"2509.09265","title":"Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents","created":"2025-09-11","cited_by_count":46,"area":"agents"},{"id":"2509.15194","title":"Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation","created":"2025-09-18","cited_by_count":45,"area":null},{"id":"2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","created":"2025-09-29","cited_by_count":42,"area":null},{"id":"2604.01193","title":"Embarrassingly Simple Self-Distillation Improves Code Generation","created":"2026-04-01","cited_by_count":40,"area":"distill"},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39,"area":"lr"},{"id":"2509.07430","title":"The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward","created":"2025-09-09","cited_by_count":37,"area":null},{"id":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"area":"lr"},{"id":"2508.11356","title":"ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism","created":"2025-08-15","cited_by_count":36,"area":null},{"id":"2512.02472","title":"Guided Self-Evolving LLMs with Minimal Human Supervision","created":"2025-12-02","cited_by_count":35,"area":null},{"id":"2508.09138","title":"Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models","created":"2025-08-12","cited_by_count":33,"area":"diffusion"},{"id":"2510.11701","title":"Demystifying Reinforcement Learning in Agentic Reasoning","created":"2025-10-13","cited_by_count":33,"area":"lr"},{"id":"2505.20282","title":"One-shot Entropy Minimization","created":"2025-05-26","cited_by_count":32,"area":null},{"id":"2505.24718","title":"Reinforcing Video Reasoning with Focused Thinking","created":"2025-05-30","cited_by_count":31,"area":"lr"},{"id":"2510.07841","title":"Self-Improving LLM Agents at Test-Time","created":"2025-10-09","cited_by_count":30,"area":"agents"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2507.03112","title":"RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents","created":"2025-07-03","cited_by_count":25,"area":"lr"},{"id":"2510.03222","title":"Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward","created":"2025-10-03","cited_by_count":25,"area":"lr"},{"id":"2603.19835","title":"FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization","created":"2026-03-20","cited_by_count":25,"area":"lr"},{"id":"2509.20357","title":"Language Models that Think, Chat Better","created":"2025-09-24","cited_by_count":24,"area":"lr"},{"id":"2609.04172","title":"Rethinking On-Policy Distillation of Large Language Models II: One Training Example","created":"2026-09-03","cited_by_count":24,"area":"distill"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2505.19640","title":"Interleaved Reasoning for Large Language Models via Reinforcement Learning","created":"2025-05-26","cited_by_count":21,"area":"lr"},{"id":"2508.02260","title":"Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning","created":"2025-08-04","cited_by_count":21,"area":"lr"},{"id":"2507.18391","title":"Revisiting LLM Reasoning via Information Bottleneck","created":"2025-07-24","cited_by_count":19,"area":"lr"},{"id":"2508.14496","title":"Semantic Energy: Detecting LLM Hallucination Beyond Entropy","created":"2025-08-20","cited_by_count":18,"area":null},{"id":"2509.14234","title":"Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision","created":"2025-09-17","cited_by_count":18,"area":null},{"id":"2603.13260","title":"Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation","created":"2026-02-25","cited_by_count":16,"area":"lr"},{"id":"2510.02172","title":"RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2506.04695","title":"Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2509.00125","title":"Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning","created":"2025-08-29","cited_by_count":12,"area":"lr"},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2509.26114","title":"Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models","created":"2025-09-30","cited_by_count":12,"area":"lr"},{"id":"2510.17472","title":"Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs","created":"2025-10-20","cited_by_count":12,"area":"lr"},{"id":"2506.10139","title":"Unsupervised Elicitation of Language Models","created":"2025-06-11","cited_by_count":11,"area":null},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2509.16591","title":"Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature","created":"2025-09-20","cited_by_count":11,"area":null},{"id":"2509.22611","title":"Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning","created":"2025-09-26","cited_by_count":11,"area":"lr"},{"id":"2602.02495","title":"Reward-free Alignment for Conflicting Objectives","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","cited_by_count":11,"area":"lr"},{"id":"2507.14783","title":"Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling","created":"2025-07-20","cited_by_count":10,"area":"lr"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2512.17951","title":"SuperFlow: Training Flow Matching Models with RL on the Fly","created":"2025-12-17","cited_by_count":10,"area":"diffusion"},{"id":"2602.19895","title":"DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2510.03632","title":"MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information","created":"2025-10-04","cited_by_count":8,"area":"lr"},{"id":"2511.11881","title":"Better LLM Reasoning via Dual-Play","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2604.11056","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","created":"2026-04-13","cited_by_count":8,"area":"lr"},{"id":"2509.05489","title":"Self-Aligned Reward: Towards Effective and Efficient Reasoners","created":"2025-09-05","cited_by_count":7,"area":"lr"},{"id":"2509.23067","title":"Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks","created":"2025-09-27","cited_by_count":7,"area":"synth"},{"id":"2512.13106","title":"TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning","created":"2025-12-15","cited_by_count":7,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2602.06019","title":"Multi-Token Prediction via Self-Distillation","created":"2026-02-05","cited_by_count":7,"area":"inference"},{"id":"2602.07276","title":"Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs","created":"2026-02-07","cited_by_count":7,"area":"mechinterp"},{"id":"2602.07729","title":"Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2605.19444","title":"Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting","created":"2026-05-19","cited_by_count":7,"area":"lr"},{"id":"2508.21188","title":"Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions","created":"2025-08-28","cited_by_count":6,"area":null},{"id":"2510.10223","title":"You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2605.25864","title":"When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards","created":"2026-05-25","cited_by_count":6,"area":"lr"},{"id":"2510.08026","title":"PEAR: Phase Entropy Aware Reward for Efficient Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5,"area":"lr"},{"id":"2509.23765","title":"Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality","created":"2025-09-28","cited_by_count":4,"area":"alignment"},{"id":"2510.01088","title":"Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense","created":"2025-10-01","cited_by_count":4,"area":"safety"},{"id":"2510.09544","title":"Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models","created":"2025-10-10","cited_by_count":4,"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":"2601.04700","title":"PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2602.18700","title":"Watermarking LLM Agent Trajectories","created":"2026-02-21","cited_by_count":4,"area":"agents"},{"id":"2603.16157","title":"DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2605.04984","title":"Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2507.18122","title":"Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning","created":"2025-07-24","cited_by_count":3,"area":"lr"},{"id":"2510.08977","title":"Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2510.09369","title":"Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2601.21804","title":"Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2602.04234","title":"When Does Multi-Agent Collaboration Help? An Entropy Perspective","created":"2026-02-04","cited_by_count":3,"area":"agents"},{"id":"2602.22751","title":"Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning","created":"2026-02-26","cited_by_count":3,"area":"lr"},{"id":"2604.06192","title":"The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2605.06241","title":"Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2605.09920","title":"Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2606.01464","title":"Cross-lingual Self-Consistency for Multilingual Reasoning with Language Models","created":"2026-05-31","cited_by_count":3,"area":"lr"},{"id":"2509.00079","title":"Entropy-Guided Loop: Achieving Reasoning through Uncertainty-Aware Generation","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2510.01527","title":"Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2510.18814","title":"A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning","created":"2025-10-21","cited_by_count":2,"area":"lr"},{"id":"2511.06380","title":"What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models","created":"2025-11-09","cited_by_count":2,"area":"lr"},{"id":"2511.18832","title":"Concept than Document: Context Compression via AMR-based Conceptual Entropy","created":"2025-11-24","cited_by_count":2,"area":"rag"},{"id":"2601.04973","title":"ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2601.14700","title":"DARL: Encouraging Diverse Answers for General Reasoning without Verifiers","created":"2026-01-21","cited_by_count":2,"area":"lr"},{"id":"2601.15690","title":"From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2603.27977","title":"SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology","created":"2026-03-30","cited_by_count":2,"area":"lr"},{"id":"2604.03993","title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","created":"2026-04-05","cited_by_count":2,"area":"lr"},{"id":"2604.05355","title":"ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning","created":"2026-04-07","cited_by_count":2,"area":"lr"},{"id":"2604.14528","title":"Dissecting Failure Dynamics in Large Language Model Reasoning","created":"2026-04-16","cited_by_count":2,"area":"lr"},{"id":"2604.18574","title":"When Can LLMs Learn to Reason with Weak Supervision?","created":"2026-04-20","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}