{"total":65,"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":"2510.24684","title":"SPICE: Self-Play In Corpus Environments Improves Reasoning","created":"2025-10-28","cited_by_count":83,"area":null},{"id":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2511.07317","title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","created":"2025-11-10","cited_by_count":50,"area":null},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"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":"2510.01135","title":"Prompt Curriculum Learning for Efficient LLM Post-Training","created":"2025-10-01","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":"2505.13445","title":"Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards","created":"2025-05-19","cited_by_count":38,"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":"2509.04419","title":"Towards a Unified View of Large Language Model Post-Training","created":"2025-09-04","cited_by_count":36,"area":null},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2505.20282","title":"One-shot Entropy Minimization","created":"2025-05-26","cited_by_count":32,"area":null},{"id":"2505.24480","title":"Towards Effective Code-Integrated Reasoning","created":"2025-05-30","cited_by_count":23,"area":null},{"id":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18,"area":null},{"id":"2512.23075","title":"Trust Region Masking for Long-Horizon LLM Reinforcement Learning","created":"2025-12-28","cited_by_count":16,"area":null},{"id":"2601.02151","title":"Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting","created":"2026-01-05","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":"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":"2604.07666","title":"An Imperfect Verifier is Good Enough: Learning with Noisy Rewards","created":"2026-04-09","cited_by_count":13,"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":"2504.13950","title":"Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain","created":"2025-04-16","cited_by_count":7,"area":null},{"id":"2506.12217","title":"From Emergence to Control: Probing and Modulating Self-Reflection in Language Models","created":"2025-06-13","cited_by_count":6,"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":"2505.20573","title":"Collision- and Reachability-Aware Multi-Robot Control with Grounded LLM Planners","created":"2025-05-26","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":"2604.07837","title":"SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility","created":"2026-04-09","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":"2506.20666","title":"Cognitive models can reveal interpretable value trade-offs in language models","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2508.08882","title":"Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2511.14275","title":"Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2602.01599","title":"The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2605.08441","title":"DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards","created":"2026-05-08","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":"2506.03077","title":"StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2512.23087","title":"Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2604.20398","title":"WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2608.12679","title":"Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies","created":"2026-08-13","cited_by_count":2,"area":null},{"id":"2508.01245","title":"WarriorMath: Enhancing the Mathematical Ability of Large Language Models with a Defect-aware Framework","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2510.03515","title":"RAPID: An Efficient Reinforcement Learning Algorithm for Small Language Models","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2601.04954","title":"Precision over Diversity: High-Precision Reward Generalizes to Robust Instruction Following","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.06911","title":"Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2603.16843","title":"Internalizing Agency from Reflective Experience","created":"2026-03-17","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":"2605.02469","title":"Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.31058","title":"Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.02252","title":"ResMerge: Residual-based Spectral Merging of Large Language Models","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.15621","title":"Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2608.03219","title":"Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains","created":"2026-08-04","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":"2511.06575","title":"CoFineLLM: Conformal Finetuning of LLMs for Language-Instructed Robot Planning","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2512.21580","title":"Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.22474","title":"Unrewarded Exploration in Large Language Models Reveals Latent Learning from Psychology","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2601.23048","title":"From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.08237","title":"Document Reconstruction Unlocks Scalable Long-Context RLVR","created":"2026-02-09","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":"2604.27308","title":"BoostLoRA: Growing Effective Rank by Boosting Adapters","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.07520","title":"TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2609.01274","title":"From Base Rollouts to RL Reasoning: A Budgeted Search Perspective","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.04735","title":"Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.33467","title":"A Cheap Verifier is Good Enough: LLM Post-training is Robust to Erroneous Rewards","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33898","title":"No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability","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":"2610.18504","title":"How Low Can You Go: Fine-Tuning LLMs with Bayesian Optimization (LlMBO)","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}