{"total":86,"rows":[{"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":"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":"2509.07430","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":"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":"2509.22485","title":"Group Critical-token Policy Optimization for Autoregressive Image Generation","created":"2025-09-26","cited_by_count":17,"area":null},{"id":"2508.13514","title":"ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs","created":"2025-08-19","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":"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":"2602.00471","title":"Dual Latent Memory for Visual Multi-agent System","created":"2026-01-31","cited_by_count":10,"area":null},{"id":"2601.08834","title":"Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR","created":"2025-12-11","cited_by_count":9,"area":null},{"id":"2602.01745","title":"Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning","created":"2026-02-02","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":"2510.05969","title":"Probing the Difficulty Perception Mechanism of Large Language Models","created":"2025-10-07","cited_by_count":8,"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":"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":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2604.05306","title":"LLMs Should Express Uncertainty Explicitly","created":"2026-04-07","cited_by_count":6,"area":null},{"id":"2506.03703","title":"Learning-at-Criticality in Large Language Models for Quantum Field Theory and Beyond","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2509.17730","title":"ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2601.19001","title":"FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning","created":"2026-01-26","cited_by_count":5,"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":"2510.08203","title":"Memory Retrieval and Consolidation in Large Language Models through Function Tokens","created":"2025-10-09","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":"2511.00833","title":"Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials","created":"2025-11-02","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":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2606.09577","title":"Code Is More Than Text: Uncertainty Estimation for Code Generation","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2606.09932","title":"When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2606.19341","title":"Native Active Perception as Reasoning for Omni-Modal Understanding","created":"2026-06-17","cited_by_count":4,"area":null},{"id":"2509.26376","title":"ScalingAR: Scaling Confidence for Autoregressive Image Generation","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2510.07896","title":"ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall","created":"2025-10-09","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":"2603.09065","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":"2511.12033","title":"EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation","created":"2025-11-15","cited_by_count":2,"area":null},{"id":"2601.04060","title":"ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2602.21215","title":"Inference-time Alignment via Sparse Junction Steering","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2603.14382","title":"StAR: Segment Anything Reasoner","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2605.01732","title":"EGAD: Entropy-Guided Adaptive Distillation for Token-Level Knowledge Transfer","created":"2026-05-03","cited_by_count":2,"area":null},{"id":"2605.22007","title":"Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2605.29782","title":"Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning","created":"2026-05-28","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":"2607.00164","title":"Verifiable Rewards for Calibrated Probabilistic Forecasting","created":"2026-06-30","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":"2601.20255","title":"HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench","created":"2026-01-28","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":"2605.18607","title":"Forecasting Downstream Performance of LLMs With Proxy Metrics","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2607.04733","title":"LP-SFT: Keeping Plausible Alternatives Alive in Supervised Fine-Tuning","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.14614","title":"Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization","created":"2026-07-16","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":"2511.17205","title":"E$^3$-Pruner: Towards Efficient, Economical, and Effective Layer Pruning for Large Language Models","created":"2025-11-21","cited_by_count":0,"area":null},{"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":"2601.21280","title":"Token Entropy Regularization for Multi-modal Antenna Affiliation Identification","created":"2026-01-29","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":"2602.01227","title":"Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority","created":"2026-02-01","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":"2603.19710","title":"AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query Recommendation","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.09492","title":"APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.09745","title":"Entropy-informed Decoding: Adaptive Information-Driven Branching","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.11328","title":"Epistemic Uncertainty for Test-Time Discovery","created":"2026-05-11","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":"2605.20369","title":"DEL: Digit Entropy Loss for Numerical Learning of Large Language Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.25381","title":"Not only where, But when: Temporal Scheduling for RLVR","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.00257","title":"ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.11189","title":"A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design","created":"2026-06-09","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":"2607.20438","title":"Preference Tuning as Spectral Update Reorganization","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2608.21501","title":"Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.01422","title":"From Rollouts to Recipes: Self-Contained Post-Training for LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.16748","title":"TIAO: Token Importance-Aware Policy Optimization for Text Summarization","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.18135","title":"DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning","created":"2026-09-16","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":"2609.34427","title":"LLMs as Adaptive Meta-Solvers: Strategy-Diverse RL for Industrial-Scale Optimization","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36587","title":"Learned Reporting Preferences in RLVR Can Conflict with the Current Request","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.36864","title":"Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.17009","title":"MaskSense: Confronting the Visual Exploration Trap in Masked Image Generation","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}