{"total":96,"rows":[{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793,"area":"mllm"},{"id":"2512.24873","title":"Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem","created":"2025-12-31","cited_by_count":30,"area":"agents"},{"id":"2603.19835","title":"FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization","created":"2026-03-20","cited_by_count":25,"area":"lr"},{"id":"2601.06487","title":"ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking","created":"2026-01-10","cited_by_count":17,"area":"agents"},{"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":"2602.20739","title":"PyVision-RL: Forging Open Agentic Vision Models via RL","created":"2026-02-24","cited_by_count":16,"area":"agents"},{"id":"2512.03746","title":"Thinking with Programming Vision: Towards a Unified View for Thinking with Images","created":"2025-12-03","cited_by_count":15,"area":"lr"},{"id":"2602.21534","title":"ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning","created":"2026-02-25","cited_by_count":13,"area":"agents"},{"id":"2606.22995","title":"Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning","created":"2026-06-22","cited_by_count":13,"area":"agents"},{"id":"2602.08711","title":"TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions","created":"2026-02-09","cited_by_count":11,"area":null},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2602.17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2602.15620","title":"STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens","created":"2026-02-17","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":"2606.06260","title":"OneReason Technical Report","created":"2026-06-04","cited_by_count":8,"area":"lr"},{"id":"2605.02909","title":"Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR","created":"2026-04-06","cited_by_count":7,"area":"lr"},{"id":"2605.07331","title":"Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective","created":"2026-05-08","cited_by_count":7,"area":"lr"},{"id":"2601.22582","title":"MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning","created":"2026-01-30","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":"2605.02572","title":"On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length","created":"2026-05-04","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2603.01501","title":"GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2603.10101","title":"CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2603.16140","title":"Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2603.17024","title":"HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning","created":"2026-03-17","cited_by_count":5,"area":"lr"},{"id":"2604.21409","title":"S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images","created":"2026-04-23","cited_by_count":5,"area":"lr"},{"id":"2607.05943","title":"SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation","created":"2026-07-07","cited_by_count":5,"area":"lr"},{"id":"2601.03661","title":"AMIR-GRPO: Inducing Implicit Preference Signals into GRPO","created":"2026-01-07","cited_by_count":4,"area":"lr"},{"id":"2602.09782","title":"Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2603.08000","title":"SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning","created":"2026-03-09","cited_by_count":4,"area":"lr"},{"id":"2603.24984","title":"MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models","created":"2026-03-26","cited_by_count":4,"area":"lr"},{"id":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2603.15432","title":"Gym-V: A Unified Vision Environment System for Agentic Vision Research","created":"2026-03-16","cited_by_count":3,"area":"agents"},{"id":"2604.10500","title":"Visual Enhanced Depth Scaling for Multimodal Latent Reasoning","created":"2026-04-12","cited_by_count":3,"area":"lr"},{"id":"2604.20733","title":"Learning from the Near Future: Temporal Self-Distillation for RLVR","created":"2026-04-22","cited_by_count":3,"area":"distill"},{"id":"2605.11775","title":"Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control","created":"2026-05-12","cited_by_count":3,"area":null},{"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":"2607.03702","title":"Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry","created":"2026-07-04","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":"2608.23664","title":"Scaling Reinforcement Learning for Diffusion Models via Velocity Matching","created":"2026-08-24","cited_by_count":3,"area":"diffusion"},{"id":"2605.08862","title":"BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.09640","title":"Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2606.21710","title":"PrivacyAlign: Contextual Privacy Alignment for LLM Agents","created":"2026-06-19","cited_by_count":2,"area":"agents"},{"id":"2607.04364","title":"RL Forgets! Towards Continual Policy Optimization","created":"2026-07-05","cited_by_count":2,"area":"mllm"},{"id":"2607.04728","title":"Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment","created":"2026-07-06","cited_by_count":2,"area":"alignment"},{"id":"2607.12820","title":"AVSCap: Orchestrating Audio-Visual Synergy for Omni-modal Video Captioning","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2601.03895","title":"All-Quadrant Bounded Clipping GRPO: Closing the Unbounded Blind Spot for Stable and Generalizable Training","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2601.21600","title":"CORE: Collaborative Reasoning via Cross Teaching","created":"2026-01-29","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":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.22859","title":"From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models","created":"2026-02-26","cited_by_count":1,"area":"mllm"},{"id":"2603.03955","title":"GIPO: Gaussian Importance Sampling Policy Optimization","created":"2026-03-04","cited_by_count":1,"area":"deeprl"},{"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":"2604.28020","title":"Cost-Aware Learning","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.08283","title":"HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.08879","title":"Preserving Foundational Capabilities in Flow-Matching VLAs through Conservative SFT","created":"2026-05-09","cited_by_count":1,"area":"vla"},{"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":"2605.16714","title":"GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction","created":"2026-05-15","cited_by_count":1,"area":null},{"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":"2605.21467","title":"DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2605.22703","title":"Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals","created":"2026-05-21","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":"2606.00395","title":"PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning","created":"2026-05-29","cited_by_count":1,"area":"moe"},{"id":"2606.16733","title":"A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2607.14506","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","created":"2026-07-16","cited_by_count":1,"area":"lr"},{"id":"2601.09285","title":"Enhancing Spatial Reasoning in Large Language Models for Metal-Organic Frameworks Structure Prediction","created":"2026-01-14","cited_by_count":0,"area":"lr"},{"id":"2602.05494","title":"A Unified Framework for Rethinking Policy Divergence Measures in GRPO","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2603.16929","title":"MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning","created":"2026-03-14","cited_by_count":0,"area":"deeprl"},{"id":"2603.27482","title":"Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning","created":"2026-03-29","cited_by_count":0,"area":"lr"},{"id":"2605.16962","title":"OmniVL-Guard Pro: A Tool-Augmented Agent for Omnibus Vision-Language Forensics","created":"2026-05-16","cited_by_count":0,"area":"agents"},{"id":"2605.21235","title":"LamPO: A Lambda Style Policy Optimization for Reasoning Language Models","created":"2026-05-20","cited_by_count":0,"area":"lr"},{"id":"2605.25582","title":"Extreme Region Policy Distillation","created":"2026-05-25","cited_by_count":0,"area":"distill"},{"id":"2606.08088","title":"ConSteer-RL: Steering Reasoning Capabilities in Large Language Models via Confidence-Aware Reinforcement Learning","created":"2026-06-06","cited_by_count":0,"area":"lr"},{"id":"2606.17735","title":"Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2607.04713","title":"RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"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":"2607.22644","title":"DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2607.23124","title":"AgentOmnia: Scaling Agentic Models for Full-Scenario Applications","created":"2026-07-25","cited_by_count":0,"area":"agents"},{"id":"2608.10149","title":"REATS: LLM Reasoning-based Ensemble Learning for Adaptive Time Series Forecasting","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2609.02170","title":"DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation","created":"2026-09-02","cited_by_count":0,"area":"alignment"},{"id":"2609.06931","title":"CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.14779","title":"Func-R1: Incentivizing Mathematical Function Reasoning in Multimodal Large Language Models","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.16748","title":"TIAO: Token Importance-Aware Policy Optimization for Text Summarization","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.28554","title":"Pistis Technical Report","created":"2026-09-23","cited_by_count":0,"area":"mllm"},{"id":"2609.28963","title":"Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2609.32674","title":"Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.40360","title":"Semifactual Credit-Augmented Policy Optimization","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.01892","title":"Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01896","title":"Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.05373","title":"Towards Unbiased On-Policy Distillation for Block Diffusion Language Models","created":"2026-10-04","cited_by_count":0,"area":"diffusion"},{"id":"2610.09914","title":"RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning","created":"2026-10-07","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"},{"id":"2610.15246","title":"ObsSpec: Accelerating Agentic Reinforcement Learning with Observation Speculation","created":"2026-10-11","cited_by_count":0,"area":"wm"},{"id":"2610.19103","title":"Contextual Credit Policy Optimization","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}