{"total":25,"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":"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":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18,"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":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"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":"2605.20854","title":"Regret Analysis of Retry-Based Bandits","created":"2026-05-20","cited_by_count":4,"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":"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":"2512.12012","title":"Semantic-Drive: Democratizing Long-Tail Data Curation via Open-Vocabulary Grounding and Neuro-Symbolic VLM Consensus","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2601.23006","title":"InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2605.10341","title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.28022","title":"Beyond pass@k: Redundancy-Aware RLVR for Multi-Sample Code Generation","created":"2026-05-27","cited_by_count":1,"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":"2607.14614","title":"Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization","created":"2026-07-16","cited_by_count":1,"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":"2607.11146","title":"Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.00296","title":"Stabilized Best-of-$K$ Training for Neural Combinatorial Optimization","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.14665","title":"When Does the Best Sampling Temperature Rise with the Budget? Sufficient Conditions for Pass@k","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.00444","title":"Group Adaptive Clipping Policy Optimization","created":"2026-08-31","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":"2610.17735","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}