{"total":83,"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":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2507.05687","title":"AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs","created":"2025-07-08","cited_by_count":40,"area":null},{"id":"2505.20315","title":"Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL","created":"2025-05-22","cited_by_count":38,"area":"lr"},{"id":"2505.17621","title":"Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Exploration","created":"2025-05-23","cited_by_count":34,"area":"lr"},{"id":"2512.02792","title":"HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval","created":"2025-12-02","cited_by_count":32,"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":"2501.14050","title":"GraphRAG under Fire","created":"2025-01-23","cited_by_count":24,"area":"rag"},{"id":"2505.22521","title":"Evaluating Supervised Learning Models for Fraud Detection: A Comparative Study of Classical and Deep Architectures on Imbalanced Transaction Data","created":"2025-05-28","cited_by_count":20,"area":null},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"id":"2601.20103","title":"Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis","created":"2026-01-27","cited_by_count":18,"area":"alignment"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2504.15659","title":"VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation","created":"2025-04-22","cited_by_count":13,"area":null},{"id":"2504.12574","title":"ForgetMe: Evaluating Selective Forgetting in Generative Models","created":"2025-04-17","cited_by_count":11,"area":"diffusion"},{"id":"2509.13723","title":"DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning","created":"2025-09-17","cited_by_count":10,"area":"lr"},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2505.06305","title":"User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2505.23017","title":"$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2505.23809","title":"LLM-Driven E-Commerce Marketing Content Optimization: Balancing Creativity and Conversion","created":"2025-05-27","cited_by_count":7,"area":null},{"id":"2601.02075","title":"MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics","created":"2026-01-05","cited_by_count":7,"area":null},{"id":"2506.05873","title":"Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks","created":"2025-06-06","cited_by_count":6,"area":null},{"id":"2506.17551","title":"Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based Recommendation Systems","created":"2025-06-21","cited_by_count":6,"area":null},{"id":"2604.09813","title":"Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning","created":"2026-04-10","cited_by_count":6,"area":"agents"},{"id":"2504.05728","title":"AI-Driven Prognostics for State of Health Prediction in Li-ion Batteries: A Comprehensive Analysis with Validation","created":"2025-04-08","cited_by_count":5,"area":null},{"id":"2506.15710","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2507.16672","title":"Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs","created":"2025-07-22","cited_by_count":5,"area":null},{"id":"2508.05289","title":"RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders","created":"2025-08-07","cited_by_count":5,"area":"alignment"},{"id":"2506.07236","title":"A Narrative Review on Large AI Models in Lung Cancer Screening, Diagnosis, and Treatment Planning","created":"2025-06-08","cited_by_count":4,"area":null},{"id":"2506.08970","title":"A Survey of Link Prediction in N-ary Knowledge Graphs","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2511.20468","title":"DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs","created":"2025-11-25","cited_by_count":4,"area":"lr"},{"id":"2605.07153","title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2605.24812","title":"CoRe-Code: Collaborative Reinforcement Learning for Code Generation","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2506.11421","title":"Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2508.02886","title":"Coherent Multimodal Reasoning with Iterative Self-Evaluation for Vision-Language Models","created":"2025-08-04","cited_by_count":3,"area":"lr"},{"id":"2510.17923","title":"Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":"alignment"},{"id":"2512.14018","title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2602.16548","title":"RIDER: 3D RNA Inverse Design with Reinforcement Learning-Guided Diffusion","created":"2026-02-18","cited_by_count":3,"area":"diffusion"},{"id":"2503.19271","title":"MARS: Memory-Enhanced Agents with Reflective Self-improvement","created":"2025-03-25","cited_by_count":2,"area":"agents"},{"id":"2507.07854","title":"Credit Risk Analysis for SMEs Using Graph Neural Networks in Supply Chain","created":"2025-07-10","cited_by_count":2,"area":null},{"id":"2507.11052","title":"LLM-Augmented Symptom Analysis for Cardiovascular Disease Risk Prediction: A Clinical NLP","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2509.13179","title":"Efficient Cold-Start Recommendation via BPE Token-Level Embedding Initialization with LLM","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2509.24257","title":"VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.23652","title":"The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2603.06065","title":"ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning","created":"2026-03-06","cited_by_count":2,"area":"agents"},{"id":"2603.11873","title":"AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization","created":"2026-03-12","cited_by_count":2,"area":"moe"},{"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":"2503.17669","title":"TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2507.04149","title":"Large Language Models for Zero-Shot Multicultural Name Recognition","created":"2025-07-05","cited_by_count":1,"area":null},{"id":"2507.21858","title":"Low-Cost Test-Time Adaptation for Robust Video Editing","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2508.03935","title":"CAP-LLM: Context-Augmented Personalized Large Language Models for News Headline Generation","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.15845","title":"Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2509.03673","title":"A Machine Learning-Based Study on the Synergistic Optimization of Supply Chain Management and Financial Supply Chains from an Economic Perspective","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.05669","title":"Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance","created":"2025-09-06","cited_by_count":1,"area":"lr"},{"id":"2509.09066","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","created":"2025-09-11","cited_by_count":1,"area":null},{"id":"2509.18130","title":"Research on Metro Transportation Flow Prediction Based on the STL-GRU Combined Model","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2509.18137","title":"LoRALib: A Standardized Benchmark for Evaluating LoRA-MoE Methods","created":"2025-09-14","cited_by_count":1,"area":"moe"},{"id":"2510.07167","title":"Reasoning for Hierarchical Text Classification: The Case of Patents","created":"2025-10-08","cited_by_count":1,"area":"lr"},{"id":"2604.18027","title":"CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora","created":"2026-04-20","cited_by_count":1,"area":"synth"},{"id":"2604.27859","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2503.17660","title":"OMR-Diffusion:Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Intent Understanding","created":"2025-03-22","cited_by_count":0,"area":"diffusion"},{"id":"2506.01118","title":"Revolutionizing Radiology Workflow with Factual and Efficient CXR Report Generation","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2506.17900","title":"Leveraging Large Language Model for Intelligent Log Processing and Autonomous Debugging in Cloud AI Platforms","created":"2025-06-22","cited_by_count":0,"area":null},{"id":"2507.04151","title":"Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2508.06624","title":"VL-MedGuide: A Visual-Linguistic Large Model for Intelligent and Explainable Skin Disease Auxiliary Diagnosis","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.01161","title":"Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkers","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2509.01164","title":"A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecture","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2509.04751","title":"Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2509.05695","title":"Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2509.05741","title":"Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification","created":"2025-09-06","cited_by_count":0,"area":"lr"},{"id":"2509.11247","title":"Contextualized Multimodal Lifelong Person Re-Identification in Hybrid Clothing States","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2510.21830","title":"GAPO: Robust Advantage Estimation for Real-World Code LLMs","created":"2025-10-22","cited_by_count":0,"area":"lr"},{"id":"2510.22075","title":"Agentic Reinforcement Learning for Real-World Code Repair","created":"2025-10-24","cited_by_count":0,"area":"agents"},{"id":"2511.00166","title":"Study on Supply Chain Finance Decision-Making Model and Enterprise Economic Performance Prediction Based on Deep Reinforcement Learning","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2511.13007","title":"GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs","created":"2025-11-17","cited_by_count":0,"area":"alignment"},{"id":"2601.09118","title":"LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.09238","title":"Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method","created":"2026-01-14","cited_by_count":0,"area":"diffusion"},{"id":"2601.20881","title":"MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreading","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.13361","title":"The Diffusion Duet: Harmonizing Dual Channels with Wavelet Suppression for Image Separation","created":"2026-02-13","cited_by_count":0,"area":"diffusion"},{"id":"2602.15903","title":"Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignment","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.00118","title":"Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.13429","title":"A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2607.05677","title":"From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software","created":"2026-07-06","cited_by_count":0,"area":"agents"}],"next_cursor":null}