{"total":193,"rows":[{"id":"2605.08063","title":"Flow-OPD: On-Policy Distillation for Flow Matching Models","created":"2026-05-08","cited_by_count":34,"area":"diffusion"},{"id":"2608.25593","title":"JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution","created":"2026-08-26","cited_by_count":16,"area":"agents"},{"id":"2607.07675","title":"Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence","created":"2026-07-08","cited_by_count":15,"area":"moe"},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2602.12205","title":"DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing","created":"2026-02-12","cited_by_count":14,"area":null},{"id":"2606.14777","title":"JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence","created":"2026-06-10","cited_by_count":14,"area":null},{"id":"2601.10201","title":"Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2602.03048","title":"CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2602.12529","title":"Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models","created":"2026-02-13","cited_by_count":12,"area":"diffusion"},{"id":"2603.00656","title":"InfoPO: Information-Driven Policy Optimization for User-Centric Agents","created":"2026-02-28","cited_by_count":12,"area":"agents"},{"id":"2605.04128","title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","created":"2026-05-05","cited_by_count":12,"area":null},{"id":"2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","created":"2026-08-19","cited_by_count":12,"area":"synth"},{"id":"2604.22840","title":"AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards","created":"2026-04-21","cited_by_count":11,"area":"agents"},{"id":"2605.20164","title":"Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR","created":"2026-05-19","cited_by_count":11,"area":null},{"id":"2604.02795","title":"Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks","created":"2026-04-03","cited_by_count":10,"area":"alignment"},{"id":"2606.11167","title":"Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models","created":"2026-06-09","cited_by_count":10,"area":null},{"id":"2602.10560","title":"When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning","created":"2026-02-11","cited_by_count":9,"area":"lr"},{"id":"2606.07412","title":"Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills","created":"2026-06-05","cited_by_count":9,"area":"agents"},{"id":"2608.11669","title":"Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL","created":"2026-08-12","cited_by_count":9,"area":"alignment"},{"id":"2601.21972","title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"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":"2605.29801","title":"AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security","created":"2026-05-28","cited_by_count":8,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2602.22732","title":"Generative Recommendation for Large-Scale Advertising","created":"2026-02-26","cited_by_count":7,"area":null},{"id":"2604.02869","title":"Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration","created":"2026-04-03","cited_by_count":7,"area":"lr"},{"id":"2605.12480","title":"OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation","created":"2026-05-12","cited_by_count":7,"area":null},{"id":"2605.26958","title":"Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation","created":"2026-05-26","cited_by_count":7,"area":"lr"},{"id":"2603.15646","title":"Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy","created":"2026-03-04","cited_by_count":6,"area":"alignment"},{"id":"2604.08476","title":"Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization","created":"2026-04-09","cited_by_count":6,"area":"lr"},{"id":"2606.11025","title":"Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models","created":"2026-06-09","cited_by_count":6,"area":"diffusion"},{"id":"2606.15441","title":"Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2603.27742","title":"TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration","created":"2026-03-29","cited_by_count":5,"area":"agents"},{"id":"2606.09701","title":"Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2606.27608","title":"Qwen-Image-2.0-RL Technical Report","created":"2026-06-25","cited_by_count":5,"area":"diffusion"},{"id":"2607.21273","title":"The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and The Channel, Not the Content, Decides What Works","created":"2026-07-23","cited_by_count":5,"area":"lr"},{"id":"2602.12395","title":"What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2602.13407","title":"On-Policy Supervised Fine-Tuning for Efficient Reasoning","created":"2026-02-13","cited_by_count":4,"area":"lr"},{"id":"2604.03581","title":"HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving","created":"2026-04-04","cited_by_count":4,"area":"driving"},{"id":"2605.13803","title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2608.20492","title":"Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs","created":"2026-08-20","cited_by_count":4,"area":"lr"},{"id":"2602.01034","title":"Discovering Process-Outcome Credit in Multi-Step LLM Reasoning","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2605.00015","title":"TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning","created":"2026-04-18","cited_by_count":3,"area":null},{"id":"2605.05750","title":"RVPO: Risk-Sensitive Alignment via Variance Regularization","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2605.13467","title":"PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2605.25604","title":"DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning","created":"2026-05-25","cited_by_count":3,"area":"alignment"},{"id":"2606.00204","title":"APE: Agentic Prompt Enhancer for Image Generation and Editing","created":"2026-05-29","cited_by_count":3,"area":"agents"},{"id":"2606.16771","title":"GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization","created":"2026-06-15","cited_by_count":3,"area":"alignment"},{"id":"2606.17362","title":"DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models","created":"2026-06-15","cited_by_count":3,"area":"lr"},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2606.26947","title":"Scaling Multi-Reference Image Generation with Dynamic Reward Optimization","created":"2026-06-25","cited_by_count":3,"area":null},{"id":"2606.31575","title":"Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index","created":"2026-06-30","cited_by_count":3,"area":"lr"},{"id":"2607.01191","title":"Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning","created":"2026-07-01","cited_by_count":3,"area":"lr"},{"id":"2608.03092","title":"SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation","created":"2026-08-04","cited_by_count":3,"area":"alignment"},{"id":"2602.05863","title":"Constrained Group Relative Policy Optimization","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.06869","title":"Uncovering Cross-Objective Interference in Multi-Objective Alignment","created":"2026-02-06","cited_by_count":2,"area":"alignment"},{"id":"2603.18118","title":"Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2605.07394","title":"BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.25443","title":"Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"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":"2606.29296","title":"Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners","created":"2026-06-28","cited_by_count":2,"area":"lr"},{"id":"2606.31711","title":"Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2606.31825","title":"Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2607.25659","title":"CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization","created":"2026-07-28","cited_by_count":2,"area":"lr"},{"id":"2608.07565","title":"What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.16072","title":"Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization","created":"2026-08-17","cited_by_count":2,"area":"lr"},{"id":"2609.00213","title":"Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning","created":"2026-08-31","cited_by_count":2,"area":"alignment"},{"id":"2601.14686","title":"IB-GRPO: Aligning LLM-based Learning Path Recommendation with Educational Objectives via Indicator-Based Group Relative Policy Optimization","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2601.21452","title":"SAGE: Sequence-level Adaptive Gradient Evolution for Generative Recommendation","created":"2026-01-29","cited_by_count":1,"area":"alignment"},{"id":"2601.22648","title":"UCPO: Uncertainty-Aware Policy Optimization","created":"2026-01-30","cited_by_count":1,"area":null},{"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":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.18528","title":"Correlation-Weighted Multi-Reward Optimization for Compositional Generation","created":"2026-03-19","cited_by_count":1,"area":"alignment"},{"id":"2603.28460","title":"$R_\\text{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation","created":"2026-03-30","cited_by_count":1,"area":"diffusion"},{"id":"2604.03098","title":"Co-Evolution of Policy and Internal Reward for Language Agents","created":"2026-04-03","cited_by_count":1,"area":"agents"},{"id":"2604.06159","title":"Target Policy Optimization","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.16893","title":"EasyVideoR1: Easier RL for Video Understanding","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2604.18187","title":"Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2604.19355","title":"LASER: Learning Active Sensing for Continuum Field Reconstruction","created":"2026-04-21","cited_by_count":1,"area":"deeprl"},{"id":"2605.06650","title":"Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.07244","title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.12667","title":"ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization","created":"2026-05-12","cited_by_count":1,"area":"alignment"},{"id":"2605.13641","title":"Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization","created":"2026-05-13","cited_by_count":1,"area":"deeprl"},{"id":"2605.18843","title":"TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.18899","title":"Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.23281","title":"DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.27820","title":"EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.29582","title":"PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2606.03329","title":"InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.05671","title":"QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.09290","title":"Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning","created":"2026-06-08","cited_by_count":1,"area":"lr"},{"id":"2607.29246","title":"Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL","created":"2026-07-31","cited_by_count":1,"area":"alignment"},{"id":"2608.08009","title":"Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation","created":"2026-08-08","cited_by_count":1,"area":"lr"},{"id":"2608.10513","title":"SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning","created":"2026-08-11","cited_by_count":1,"area":"mllm"},{"id":"2608.15763","title":"Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report","created":"2026-08-16","cited_by_count":1,"area":"agents"},{"id":"2608.30632","title":"GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning","created":"2026-08-31","cited_by_count":1,"area":"lr"},{"id":"2609.01409","title":"EdiTikZ: Scientific Figure Editing from Revision Trajectories","created":"2026-09-01","cited_by_count":1,"area":"mllm"},{"id":"2609.07072","title":"Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2609.08211","title":"A Better Spur Should Start From Each Objective","created":"2026-09-08","cited_by_count":1,"area":"deeprl"},{"id":"2609.19164","title":"Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.24259","title":"MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents","created":"2026-09-21","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}