{"total":146,"rows":[{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497,"area":null},{"id":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2510.18927","title":"BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping","created":"2025-10-21","cited_by_count":47,"area":null},{"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":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"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":"2511.14617","title":"Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning","created":"2025-11-18","cited_by_count":25,"area":null},{"id":"2510.06062","title":"When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL","created":"2025-10-07","cited_by_count":21,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2511.17826","title":"Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch","created":"2025-11-21","cited_by_count":14,"area":null},{"id":"2604.07666","title":"An Imperfect Verifier is Good Enough: Learning with Noisy Rewards","created":"2026-04-09","cited_by_count":13,"area":null},{"id":"2512.06547","title":"A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation","created":"2025-12-06","cited_by_count":12,"area":null},{"id":"2512.10551","title":"LLM-Auction: Generative Auction towards LLM-Native Advertising","created":"2025-12-11","cited_by_count":12,"area":null},{"id":"2601.07348","title":"Controlled Self-Evolution for Algorithmic Code Optimization","created":"2026-01-12","cited_by_count":12,"area":null},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"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":"2510.19338","title":"Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2512.10949","title":"Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation","created":"2025-12-11","cited_by_count":10,"area":null},{"id":"2606.13368","title":"IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing","created":"2026-06-11","cited_by_count":10,"area":null},{"id":"2602.01826","title":"Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2606.12370","title":"Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling","created":"2026-06-10","cited_by_count":9,"area":null},{"id":"2602.03392","title":"On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":8,"area":null},{"id":"2602.20532","title":"Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Training","created":"2026-02-24","cited_by_count":8,"area":null},{"id":"2509.09177","title":"Clip Your Sequences Fairly: Enforcing Length Fairness for Sequence-Level RL","created":"2025-09-11","cited_by_count":7,"area":null},{"id":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2602.20913","title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2509.13642","title":"LLM-I: LLMs are Naturally Interleaved Multimodal Creators","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2512.13874","title":"SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning","created":"2025-12-15","cited_by_count":6,"area":null},{"id":"2602.07078","title":"The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL","created":"2026-02-06","cited_by_count":6,"area":null},{"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":"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":"2509.17730","title":"ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2601.10029","title":"PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization","created":"2026-01-15","cited_by_count":5,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"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":"2603.15370","title":"Trajectory-Diversity-Driven Robust Vision-and-Language Navigation","created":"2026-03-16","cited_by_count":5,"area":null},{"id":"2606.27974","title":"ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering","created":"2026-06-26","cited_by_count":5,"area":null},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2510.08549","title":"Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2603.23550","title":"Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction","created":"2026-03-21","cited_by_count":4,"area":null},{"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":"2510.22101","title":"Scaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2510.25441","title":"Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2512.20061","title":"Scaling Reinforcement Learning for Content Moderation with Large Language Models","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2602.01599","title":"The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.23823","title":"APPO: Attention-guided Perception Policy Optimization for Video Reasoning","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2603.09740","title":"Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2603.19470","title":"Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2605.01638","title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","created":"2026-05-02","cited_by_count":3,"area":null},{"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":"2509.22480","title":"Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2602.00082","title":"Design and Empirical Study of a Large Language Model-Based Multi-Agent Investment System for Chinese Public REITs","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2603.24093","title":"Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2605.09291","title":"dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models","created":"2026-05-10","cited_by_count":2,"area":null},{"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":"2605.17648","title":"SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2606.09092","title":"From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2607.07435","title":"RLVP: Penalize the Path, Reward the Outcome","created":"2026-07-08","cited_by_count":2,"area":null},{"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":"2607.28638","title":"Learning Stateful Predictive Knowledge From Experience","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"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":"2510.22477","title":"Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2601.05578","title":"Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2601.16354","title":"NOIR: Privacy-Preserving Generation of Code with Open-Source LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"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":"2602.18915","title":"AAVGen: Precision Engineering of Adeno-associated Viral Capsids for Renal Selective Targeting","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2603.00963","title":"Stabilizing Policy Optimization via Logits Convexity","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2603.14880","title":"RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation","created":"2026-03-16","cited_by_count":1,"area":null},{"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":"2605.23281","title":"DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.31455","title":"DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.08982","title":"Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care","created":"2026-06-08","cited_by_count":1,"area":null},{"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":"2608.01418","title":"Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2609.05141","title":"SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2609.08368","title":"Miles v0.1: Production-Level Post-Training","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2601.10498","title":"PROMA: Projected Microbatch Accumulation for Reference-Free Proximal Policy Updates","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.22474","title":"Unrewarded Exploration in Large Language Models Reveals Latent Learning from Psychology","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2601.22532","title":"Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.05933","title":"Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.07014","title":"Vectra: A New Metric, Dataset, and Model for Visual Quality Assessment in E-Commerce In-Image Machine Translation","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.15913","title":"Foundation Models for Medical Imaging: Status, Challenges, and Directions","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.22033","title":"RT-RMOT: A Dataset and Framework for RGB-Thermal Referring Multi-Object Tracking","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.00377","title":"Improving Full Waveform Inversion in Large Model Era","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.06677","title":"Chart Deep Research in LVLMs via Parallel Relative Policy Optimization","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.14463","title":"An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.08986","title":"PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.14518","title":"Mind DeepResearch Technical Report","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.11235","title":"Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.14040","title":"Physics-R1: An Audited Olympiad Corpus and Released Verifiers for Visual Physics Reasoning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.17295","title":"DISA: Offline Importance Sampling for Distribution-Matching LLM-RL","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.18822","title":"Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.25381","title":"Not only where, But when: Temporal Scheduling for RLVR","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.25527","title":"DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.28109","title":"Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":"100"}