{"total":89,"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":"2509.02479","title":"SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning","created":"2025-09-02","cited_by_count":146,"area":"lr"},{"id":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"area":"lr"},{"id":"2601.08521","title":"Your Group-Relative Advantage Is Biased","created":"2026-01-13","cited_by_count":34,"area":"lr"},{"id":"2510.11701","title":"Demystifying Reinforcement Learning in Agentic Reasoning","created":"2025-10-13","cited_by_count":33,"area":"lr"},{"id":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2606.22600","title":"On the Position Bias of On-Policy Distillation","created":"2026-06-21","cited_by_count":26,"area":"lr"},{"id":"2510.03222","title":"Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward","created":"2025-10-03","cited_by_count":25,"area":"lr"},{"id":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2512.21625","title":"Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards","created":"2025-12-25","cited_by_count":19,"area":"lr"},{"id":"2601.20614","title":"Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation","created":"2026-01-28","cited_by_count":19,"area":"lr"},{"id":"2602.04663","title":"Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design","created":"2026-02-04","cited_by_count":17,"area":"lr"},{"id":"2509.24203","title":"Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2509.25027","title":"STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2603.22117","title":"On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation","created":"2026-03-23","cited_by_count":13,"area":"lr"},{"id":"2510.19225","title":"RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs","created":"2025-10-22","cited_by_count":11,"area":"lr"},{"id":"2510.24694","title":"Repurposing Synthetic Data for Fine-grained Search Agent Supervision","created":"2025-10-28","cited_by_count":11,"area":"lr"},{"id":"2512.13278","title":"AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning","created":"2025-12-15","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":"2509.24494","title":"Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2509.24981","title":"Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2510.01656","title":"Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2510.06870","title":"$\\lambda$-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2603.13134","title":"When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO","created":"2026-03-13","cited_by_count":10,"area":"lr"},{"id":"2510.14321","title":"Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2512.00499","title":"ESPO: Entropy Importance Sampling Policy Optimization","created":"2025-11-29","cited_by_count":9,"area":"lr"},{"id":"2604.08865","title":"SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks","created":"2026-04-10","cited_by_count":9,"area":"lr"},{"id":"2602.00173","title":"Learning Robust Reasoning through Guided Adversarial Self-Play","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2605.19282","title":"Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2510.23027","title":"Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts","created":"2025-10-27","cited_by_count":6,"area":"lr"},{"id":"2602.11455","title":"Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning","created":"2026-02-12","cited_by_count":6,"area":"lr"},{"id":"2603.28204","title":"ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models","created":"2026-03-30","cited_by_count":6,"area":"lr"},{"id":"2511.04256","title":"SSPO: Subsentence-level Policy Optimization","created":"2025-11-06","cited_by_count":5,"area":"lr"},{"id":"2603.10101","title":"CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2604.01591","title":"ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement","created":"2026-04-02","cited_by_count":5,"area":"lr"},{"id":"2510.08899","title":"Pinpointing crucial steps: Attribution-based Credit Assignment for Verifiable Reinforcement Learning","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2512.08511","title":"Thinking with Images via Self-Calling Agent","created":"2025-12-09","cited_by_count":4,"area":"lr"},{"id":"2605.15980","title":"Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization","created":"2026-05-15","cited_by_count":4,"area":"lr"},{"id":"2605.21851","title":"OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning","created":"2026-05-21","cited_by_count":4,"area":"lr"},{"id":"2509.23746","title":"Poivre: Self-Refining Visual Pointing with Reinforcement Learning","created":"2025-09-28","cited_by_count":3,"area":"lr"},{"id":"2601.04714","title":"ThinkDrive: Chain-of-Thought Guided Progressive Reinforcement Learning Fine-Tuning for Autonomous Driving","created":"2026-01-08","cited_by_count":3,"area":"lr"},{"id":"2602.01103","title":"Probing RLVR training instability through the lens of objective-level hacking","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2602.04620","title":"QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2604.28005","title":"Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning","created":"2026-04-30","cited_by_count":3,"area":"lr"},{"id":"2605.04077","title":"Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO","created":"2026-04-14","cited_by_count":3,"area":"lr"},{"id":"2605.08873","title":"CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2605.10937","title":"Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping","created":"2026-05-11","cited_by_count":3,"area":"lr"},{"id":"2606.10968","title":"Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2606.18954","title":"GraphPO: Graph-based Policy Optimization for Reasoning Models","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2607.10169","title":"Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization","created":"2026-07-11","cited_by_count":3,"area":"lr"},{"id":"2512.07710","title":"Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE","created":"2025-12-08","cited_by_count":2,"area":"lr"},{"id":"2512.12576","title":"Coupled Variational Reinforcement Learning for Language Model General Reasoning","created":"2025-12-14","cited_by_count":2,"area":"lr"},{"id":"2601.03969","title":"Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models","created":"2026-01-07","cited_by_count":2,"area":"lr"},{"id":"2602.00085","title":"CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":"lr"},{"id":"2605.06523","title":"On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2510.23868","title":"GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA","created":"2025-10-27","cited_by_count":1,"area":"lr"},{"id":"2601.22521","title":"One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.03102","title":"Consensus Group Relative Policy Optimization for Text Generation","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2602.03190","title":"PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2602.06475","title":"Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2604.08690","title":"Skip-Connected Policy Optimization for Implicit Advantage","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.27859","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2605.12969","title":"Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.20865","title":"Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2605.30789","title":"Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.07000","title":"Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization","created":"2026-06-05","cited_by_count":1,"area":"lr"},{"id":"2510.09255","title":"DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning","created":"2025-10-10","cited_by_count":0,"area":"lr"},{"id":"2510.21830","title":"GAPO: Robust Advantage Estimation for Real-World Code LLMs","created":"2025-10-22","cited_by_count":0,"area":"lr"},{"id":"2602.14169","title":"Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2602.19327","title":"Soft Sequence Policy Optimization","created":"2026-02-22","cited_by_count":0,"area":"lr"},{"id":"2604.02007","title":"Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2605.04066","title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","created":"2026-04-11","cited_by_count":0,"area":"lr"},{"id":"2605.12058","title":"Holder Policy Optimisation","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2606.03234","title":"Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.10931","title":"It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.13316","title":"ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.28166","title":"Tandem Reinforcement Learning with Verifiable Rewards","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2606.28692","title":"An AI agent for treatment reasoning over a biomedical tool universe","created":"2026-06-27","cited_by_count":0,"area":"lr"},{"id":"2607.02504","title":"Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.06987","title":"UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2608.11674","title":"GCPO: Diagnosing and Constraining Subspace Geometry in Rollout RL for LLMs","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2608.17301","title":"SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2608.27982","title":"Learning from Hard Prompts: Difficulty-aware Advantage Amplification in Dynamic Sampling","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.04063","title":"Spurious Advantage Hidden in GRPO","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.21432","title":"GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.33970","title":"On the Token Value Inequality in Efficient Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.39402","title":"Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.13015","title":"Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.13020","title":"Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}