{"total":90,"rows":[{"id":"2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","created":"2025-10-15","cited_by_count":101,"area":null},{"id":"2507.14843","title":"The Invisible Leash: Why RLVR May or May Not Escape Its Origin","created":"2025-07-20","cited_by_count":97,"area":null},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2510.18927","title":"BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping","created":"2025-10-21","cited_by_count":47,"area":null},{"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":"2509.03493","title":"On Entropy Control in LLM-RL Algorithms","created":"2025-09-03","cited_by_count":40,"area":null},{"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":"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":"2509.04419","title":"Towards a Unified View of Large Language Model Post-Training","created":"2025-09-04","cited_by_count":36,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32,"area":null},{"id":"2602.13035","title":"Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL","created":"2026-02-13","cited_by_count":27,"area":null},{"id":"2508.14496","title":"Semantic Energy: Detecting LLM Hallucination Beyond Entropy","created":"2025-08-20","cited_by_count":18,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2510.23393","title":"The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation","created":"2025-10-27","cited_by_count":16,"area":null},{"id":"2510.05837","title":"EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2511.15248","title":"EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control","created":"2025-11-19","cited_by_count":13,"area":null},{"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":"2602.01826","title":"Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2604.08706","title":"Efficient RL Training for LLMs with Experience Replay","created":"2026-04-09","cited_by_count":9,"area":null},{"id":"2605.00365","title":"Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity","created":"2026-05-01","cited_by_count":9,"area":null},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2511.14045","title":"Auditing Data Membership in Reinforcement Learning With Verifiable Rewards","created":"2025-11-18","cited_by_count":8,"area":null},{"id":"2602.03392","title":"On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":8,"area":null},{"id":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2605.21801","title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2603.12151","title":"IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL","created":"2026-03-12","cited_by_count":6,"area":null},{"id":"2605.12484","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2605.25459","title":"From Simulation to Enaction: Post-trained language models recognize and react to their own generations","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2602.05717","title":"Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2602.12351","title":"LongNav-R1: Horizon-Adaptive Multi-Turn RL for Long-Horizon VLA Navigation","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2509.22613","title":"Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2509.25774","title":"PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2509.26093","title":"Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Experts","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2510.08549","title":"Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2601.15609","title":"When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards","created":"2026-01-22","cited_by_count":4,"area":null},{"id":"2602.03075","title":"ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution","created":"2026-02-03","cited_by_count":4,"area":null},{"id":"2507.13874","title":"Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Models","created":"2025-07-18","cited_by_count":3,"area":null},{"id":"2601.04544","title":"TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2603.04918","title":"BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2603.09065","title":"Learning Adaptive LLM Decoding","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2605.08666","title":"The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2605.11775","title":"Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2607.07674","title":"Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2607.16850","title":"Group Entropy-Controlled Policy Optimization","created":"2026-07-18","cited_by_count":3,"area":null},{"id":"2601.03725","title":"EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2601.15330","title":"ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2605.28751","title":"Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2606.13125","title":"Select and Improve: Understanding the Mechanics of Post-Training for Reasoning","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2601.12730","title":"Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.00938","title":"Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2603.00963","title":"Stabilizing Policy Optimization via Logits Convexity","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2603.19255","title":"LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2603.24989","title":"Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.03472","title":"Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.19063","title":"Mapping Uncharted Symmetries: Machine Discovery in Combinatorics","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.20740","title":"Reinforcement Learning over Predictive Distributions for LLM Regression","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.03087","title":"Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.18487","title":"SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.22164","title":"Drowning in Routine: Signal Dilution in Multi-Turn Agent Training","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2608.09805","title":"Parameter Exploration for RLVR via Variational Learning","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.40115","title":"Unlearnable, or Unmeasured? On the Reliability of Difficulty Labels in RLVR","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2510.19893","title":"EQPO: Equitable Group Relative Policy Optimization for Clinical Reasoning","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2601.18588","title":"Stability as a Liability:Systematic Breakdown of Linguistic Structure in LLMs","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2601.22532","title":"Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.03635","title":"TRE: Encouraging Exploration in the Trust Region","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2603.06397","title":"Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.12875","title":"Test-time RL alignment exposes task familiarity artifacts in LLM benchmarks","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.17295","title":"DISA: Offline Importance Sampling for Distribution-Matching LLM-RL","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.28109","title":"Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.31034","title":"Annealed Softmax Greedy in Many-Armed Bayesian Bandits","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.27369","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.02390","title":"DecompRL: Solving Harder Problems by Learning Modular Code Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.27757","title":"Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.05842","title":"Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.20715","title":"Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.33589","title":"TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34427","title":"LLMs as Adaptive Meta-Solvers: Strategy-Diverse RL for Industrial-Scale Optimization","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01382","title":"Gacha Decoding: Eliciting Diverse Generations Through Instruction Following","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04011","title":"Exploration-Preserving Policy Optimization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.10536","title":"Decoupling Exploration from Optimization in RLVR","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11064","title":"Measuring and Mitigating Solution Mode Collapse in RLVR","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12995","title":"What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16105","title":"Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17093","title":"SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}