{"total":91,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"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":"2509.04419","title":"Towards a Unified View of Large Language Model Post-Training","created":"2025-09-04","cited_by_count":36,"area":null},{"id":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"area":"lr"},{"id":"2509.06948","title":"Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning","created":"2025-09-08","cited_by_count":30,"area":"lr"},{"id":"2509.23352","title":"Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling","created":"2025-09-27","cited_by_count":18,"area":"diffusion"},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2509.06923","title":"Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding","created":"2025-09-08","cited_by_count":16,"area":"lr"},{"id":"2509.10396","title":"Inpainting-Guided Policy Optimization for Diffusion Large Language Models","created":"2025-09-12","cited_by_count":16,"area":"diffusion"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"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":"2510.09388","title":"Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts","created":"2025-10-10","cited_by_count":14,"area":"lr"},{"id":"2605.13230","title":"Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence","created":"2026-05-13","cited_by_count":13,"area":"lr"},{"id":"2606.09304","title":"SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling","created":"2026-06-08","cited_by_count":13,"area":"lr"},{"id":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","cited_by_count":11,"area":"agents"},{"id":"2510.26575","title":"InfoFlow: Reinforcing Search Agent Via Reward Density Optimization","created":"2025-10-30","cited_by_count":11,"area":"agents"},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2609.04108","title":"Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR","created":"2026-09-03","cited_by_count":11,"area":"lr"},{"id":"2512.06337","title":"DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization","created":"2025-12-06","cited_by_count":9,"area":"lr"},{"id":"2602.02244","title":"Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2604.23747","title":"SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning","created":"2026-04-26","cited_by_count":9,"area":"lr"},{"id":"2510.04140","title":"Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs","created":"2025-10-05","cited_by_count":7,"area":"lr"},{"id":"2602.07464","title":"SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2602.22732","title":"Generative Recommendation for Large-Scale Advertising","created":"2026-02-26","cited_by_count":7,"area":null},{"id":"2607.19313","title":"Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information","created":"2026-07-21","cited_by_count":7,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2603.03078","title":"RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization","created":"2026-03-03","cited_by_count":6,"area":"rag"},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2511.17652","title":"TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots","created":"2025-11-20","cited_by_count":5,"area":"lr"},{"id":"2607.28449","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2510.08048","title":"TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance","created":"2025-10-09","cited_by_count":4,"area":"alignment"},{"id":"2512.00706","title":"Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation","created":"2025-11-30","cited_by_count":4,"area":"mllm"},{"id":"2604.19945","title":"Visual Reasoning through Tool-supervised Reinforcement Learning","created":"2026-04-21","cited_by_count":4,"area":"lr"},{"id":"2605.12004","title":"Learning Agentic Policy from Action Guidance","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2606.09932","title":"When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2510.02227","title":"More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration","created":"2025-10-02","cited_by_count":3,"area":"lr"},{"id":"2510.04204","title":"CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling","created":"2025-10-05","cited_by_count":3,"area":"lr"},{"id":"2510.26109","title":"Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2511.09222","title":"Toward Honest Language Models for Deductive Reasoning","created":"2025-11-12","cited_by_count":3,"area":"lr"},{"id":"2511.16602","title":"Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2602.03309","title":"Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2604.14932","title":"WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2606.16215","title":"PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2511.04285","title":"RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization","created":"2025-11-06","cited_by_count":2,"area":"lr"},{"id":"2511.21056","title":"Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2512.11470","title":"Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning","created":"2025-12-12","cited_by_count":2,"area":"lr"},{"id":"2601.09233","title":"GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2603.16206","title":"Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical Reasoning","created":"2026-03-17","cited_by_count":2,"area":"lr"},{"id":"2605.04920","title":"Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization","created":"2026-05-06","cited_by_count":2,"area":"deeprl"},{"id":"2605.06326","title":"Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2606.18521","title":"Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2606.30420","title":"Experience Augmented Policy Optimization for LLM Reasoning","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2509.18600","title":"OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2509.25148","title":"AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models","created":"2025-09-29","cited_by_count":1,"area":"alignment"},{"id":"2601.12730","title":"Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2601.21476","title":"Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.10740","title":"Reinforced Curriculum Pre-Alignment for Domain-Adaptive VLMs","created":"2026-02-11","cited_by_count":1,"area":"mllm"},{"id":"2602.20197","title":"Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2603.22267","title":"TiCo: Time-Controllable Spoken Dialogue Model","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.08926","title":"Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2604.14258","title":"GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.26184","title":"GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.29303","title":"Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.04272","title":"RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2510.10606","title":"ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2602.10819","title":"RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization","created":"2026-02-11","cited_by_count":0,"area":"alignment"},{"id":"2602.11220","title":"Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT","created":"2026-02-11","cited_by_count":0,"area":"agents"},{"id":"2603.18953","title":"Context Bootstrapped Reinforcement Learning","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2604.02006","title":"ProCeedRL: Process Critic with Exploratory Demonstration Reinforcement Learning for LLM Agentic Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"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":"2604.11510","title":"Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.18530","title":"OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning","created":"2026-04-20","cited_by_count":0,"area":"lr"},{"id":"2605.08401","title":"AIPO: Learning to Reason from Active Interaction","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.15012","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2607.29211","title":"Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning","created":"2026-07-31","cited_by_count":0,"area":"lr"},{"id":"2608.06013","title":"OneEmo: A Unified Multimodal Reasoning Model for Emotion Perception, Understanding, and Interaction","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2609.00734","title":"Online Self-Weighted Fine-Tuning","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.28570","title":"DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.34036","title":"UOPD: Uncertainty-Aware Intervention for On-Policy Distillation of Multi-Turn Agents","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2609.37898","title":"Guide, Then Let Go: Gap-Adaptive Teacher Scheduling for Sparse-Reward Agentic RL","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.05966","title":"HuatuoGPT-3: RL-Only Domain Adaptation from Base Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07342","title":"Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.12914","title":"OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models","created":"2026-10-09","cited_by_count":0,"area":"vla"}],"next_cursor":null}