{"total":31,"rows":[{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"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":"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":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","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":"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":"2510.03199","title":"Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling","created":"2025-10-03","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":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2512.14754","title":"Revisiting the Reliability of Language Models in Instruction-Following","created":"2025-12-15","cited_by_count":7,"area":null},{"id":"2510.01143","title":"Generalized Parallel Scaling with Interdependent Generations","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2510.26697","title":"The End of Manual Decoding: Towards Truly End-to-End Language Models","created":"2025-10-30","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":"2605.20854","title":"Regret Analysis of Retry-Based Bandits","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2607.27372","title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2509.23595","title":"Timber: Training-free Instruct Model Refining with Base via Effective Rank","created":"2025-09-28","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":"2606.17514","title":"Unlocking LLM Code Correction with Iterative Feedback Loops","created":"2026-06-16","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":"2609.37633","title":"RLTL;DR: Self-improvement by Internalizing Self-generated Feedback","created":"2026-09-29","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":"2605.21792","title":"Residual Skill Optimization for Text-to-SQL Ensembles","created":"2026-05-20","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":"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":"2609.31688","title":"Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage","created":"2026-09-16","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":"2610.04011","title":"Exploration-Preserving Policy Optimization","created":"2026-10-02","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":"2610.16105","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":"2610.17735","title":"Train for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}