{"total":41,"rows":[{"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":"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":"2505.17826","title":"Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models","created":"2025-05-23","cited_by_count":19,"area":null},{"id":"2604.07853","title":"QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch","created":"2026-04-09","cited_by_count":7,"area":null},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2512.09756","title":"MOA: Multi-Objective Alignment for Role-Playing Agents","created":"2025-12-10","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":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","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":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2604.14932","title":"WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training","created":"2026-04-16","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":"2602.00513","title":"Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2604.16995","title":"SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models","created":"2026-04-18","cited_by_count":2,"area":null},{"id":"2607.07435","title":"RLVP: Penalize the Path, Reward the Outcome","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2510.06270","title":"MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2602.16833","title":"VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.14258","title":"GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.00610","title":"Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.26184","title":"GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.26971","title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.29303","title":"Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.04272","title":"RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2609.33085","title":"The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration","created":"2026-09-27","cited_by_count":1,"area":null},{"id":"2509.25240","title":"HAMMER: Hamiltonian Curiosity Augmented Large Language Model Reinforcement","created":"2025-09-25","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":"2604.07747","title":"Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.11522","title":"Triviality Corrected Endogenous Reward","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.12160","title":"PubSwap: Public-Data Off-Policy Coordination for Federated RLVR","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2606.04095","title":"POLARIS: Guiding Small Models to Write Long Stories","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2608.13622","title":"ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.25243","title":"From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.12419","title":"MInTRL: Off-policy Intervention can boost On-policy RL","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.33722","title":"BOReFT: Manifold Steering of Language Models for Black-box Optimization","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33796","title":"RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.05966","title":"HuatuoGPT-3: RL-Only Domain Adaptation from Base Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06861","title":"When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2610.13470","title":"GraftOOD: Grafting Out-of-Distribution Exemplars into Advantage-Weighted Rectification for Video Reward Optimization","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}