{"total":36,"rows":[{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2507.05386","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","created":"2025-07-07","cited_by_count":47,"area":null},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2509.25849","title":"Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation","created":"2025-09-30","cited_by_count":22,"area":null},{"id":"2506.02281","title":"Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"id":"2602.17616","title":"Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs","created":"2026-02-19","cited_by_count":11,"area":null},{"id":"2504.13178","title":"Aligning Constraint Generation with Design Intent in Parametric CAD","created":"2025-04-17","cited_by_count":8,"area":null},{"id":"2602.07078","title":"The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL","created":"2026-02-06","cited_by_count":6,"area":null},{"id":"2503.21383","title":"Controlling Large Language Model with Latent Actions","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2603.10848","title":"$V_{0.5}$: Generalist Value Model as a Prior for Sparse RL Rollouts","created":"2026-03-11","cited_by_count":5,"area":null},{"id":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2510.09103","title":"AdaPM: a Partial Momentum Algorithm for LLM Training","created":"2025-10-10","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":"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":"2607.20543","title":"When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion","created":"2026-07-12","cited_by_count":3,"area":null},{"id":"2608.11772","title":"Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction","created":"2026-08-12","cited_by_count":3,"area":null},{"id":"2512.16565","title":"Non-Asymptotic Global Convergence of PPO-Clip","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2608.29296","title":"When Do Larger Batches Help Scale LLM Reinforcement Learning?","created":"2026-08-29","cited_by_count":2,"area":null},{"id":"2504.13471","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2511.23310","title":"Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2512.21450","title":"RLLaVA: An RL-central Framework for Language and Vision Assistants","created":"2025-12-25","cited_by_count":1,"area":null},{"id":"2601.09428","title":"Draw it like Euclid: Teaching transformer models to generate CAD profiles using ruler and compass construction steps","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2604.06159","title":"Target Policy Optimization","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2609.34645","title":"Nereus: Adaptive Parallelism for LLM Post-Training","created":"2026-09-28","cited_by_count":1,"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":"2605.11235","title":"Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.12207","title":"Not How Many, But Which: Parameter Placement in Low-Rank Adaptation","created":"2026-05-12","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":"2606.24369","title":"Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.07419","title":"Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.26355","title":"PACT: From Credit Assignment to Critic Alignment","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.35392","title":"The Hidden Ratio in Adam: Stable Structure, Compression, and Sign Dynamics","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.03872","title":"Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery","created":"2026-10-02","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}],"next_cursor":null}