{"total":87,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.10751","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models","created":"2025-08-14","cited_by_count":138,"area":"lr"},{"id":"2601.18779","title":"POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration","created":"2026-01-26","cited_by_count":42,"area":"lr"},{"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":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"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":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2511.06411","title":"SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization","created":"2025-11-09","cited_by_count":21,"area":"lr"},{"id":"2510.10409","title":"Trace Length is a Simple Uncertainty Signal in Reasoning Models","created":"2025-10-12","cited_by_count":19,"area":"lr"},{"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":"2509.24261","title":"Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models","created":"2025-09-29","cited_by_count":14,"area":"lr"},{"id":"2509.25004","title":"CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning","created":"2025-09-29","cited_by_count":13,"area":"lr"},{"id":"2509.19249","title":"Reinforcement Learning on Pre-Training Data","created":"2025-09-23","cited_by_count":12,"area":"lr"},{"id":"2511.16231","title":"Pass@k Metric for RLVR: A Diagnostic Tool of Exploration, But Not an Objective","created":"2025-11-20","cited_by_count":12,"area":"lr"},{"id":"2601.08763","title":"Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs","created":"2026-01-13","cited_by_count":12,"area":"lr"},{"id":"2510.23049","title":"Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients","created":"2025-10-27","cited_by_count":11,"area":"lr"},{"id":"2602.01062","title":"SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2510.03669","title":"Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning","created":"2025-10-04","cited_by_count":10,"area":"lr"},{"id":"2606.15455","title":"Understanding Diversity Collapse in RLVR via the Lens of Overtraining","created":"2026-06-13","cited_by_count":10,"area":"lr"},{"id":"2601.05432","title":"Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization","created":"2026-01-08","cited_by_count":9,"area":"lr"},{"id":"2602.19895","title":"DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2602.21189","title":"Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"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":"2607.28568","title":"Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering","created":"2026-07-30","cited_by_count":8,"area":"synth"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2602.05548","title":"Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation","created":"2026-02-05","cited_by_count":7,"area":"lr"},{"id":"2603.24844","title":"Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models","created":"2026-03-25","cited_by_count":6,"area":"lr"},{"id":"2605.00380","title":"ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning","created":"2026-05-01","cited_by_count":6,"area":"lr"},{"id":"2510.01444","title":"Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"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":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2605.07039","title":"PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2605.15726","title":"Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR","created":"2026-05-15","cited_by_count":4,"area":"lr"},{"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":"2603.18886","title":"Reasoning over mathematical objects: on-policy reward modeling and test time aggregation","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2605.17333","title":"Leveraging Error Diversity in Group Rollouts for Reinforcement Learning","created":"2026-05-17","cited_by_count":3,"area":"lr"},{"id":"2605.18864","title":"SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs","created":"2026-05-15","cited_by_count":3,"area":"lr"},{"id":"2606.10385","title":"Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2606.03962","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.06096","title":"OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2607.14962","title":"Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation","created":"2026-07-16","cited_by_count":2,"area":"deeprl"},{"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":"2602.01603","title":"Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"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":"2605.11461","title":"Breaking $\\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.15464","title":"GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero","created":"2026-05-14","cited_by_count":1,"area":"alignment"},{"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":"2606.03608","title":"Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.05888","title":"Retry Policy Gradients in Continuous Action Spaces","created":"2026-06-04","cited_by_count":1,"area":"deeprl"},{"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":"2607.03065","title":"Spectral Rewiring for Exploration, Purification, and Model Merging","created":"2026-07-03","cited_by_count":1,"area":"lr"},{"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":"2608.06582","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","created":"2026-08-06","cited_by_count":1,"area":"deeprl"},{"id":"2603.18088","title":"Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.13902","title":"DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2605.10716","title":"What should post-training optimize? A test-time scaling law perspective","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.21792","title":"Residual Skill Optimization for Text-to-SQL Ensembles","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.29190","title":"When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.18910","title":"REVES: REvision and VErification--Augmented Training for Test-Time Scaling","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2607.01490","title":"Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"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":"2607.17823","title":"Theoretical Foundations of $\\max$@$k$ Reinforcement Learning","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"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":"2608.21305","title":"Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2609.00444","title":"Group Adaptive Clipping Policy Optimization","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.25510","title":"Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.27374","title":"Planned Test-Time Scaling with Coordinated Reasoning Paths","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.33291","title":"The Statistical Benefits of Multiple Responses for Learning from Demonstrations","created":"2026-09-27","cited_by_count":0,"area":"offlinerl"},{"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":"2609.34929","title":"Sample What You Say: Aligning Language Models to Sample the Distributions They State","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.36552","title":"SERA: Scale-Equalized Rollout Allocation for Maximum Likelihood Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38018","title":"Prompts Live on an Arc: Gaussian Curricula in Fisher--Rao Coordinates for Rollout-Efficient GRPO","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.00661","title":"Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.02478","title":"Tropical Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"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},{"id":"2610.19133","title":"TRACER: Trace-Regularized Training Against Indirect Prompt Injection","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}