{"total":30,"rows":[{"id":"2506.09026","title":"e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2505.12929","title":"Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs","created":"2025-05-19","cited_by_count":44,"area":"lr"},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37,"area":"lr"},{"id":"2505.18830","title":"On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization","created":"2025-05-24","cited_by_count":31,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2507.23779","title":"Phi-Ground Tech Report: Advancing Perception in GUI Grounding","created":"2025-07-31","cited_by_count":25,"area":"lr"},{"id":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2510.02230","title":"The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models","created":"2025-10-02","cited_by_count":18,"area":"lr"},{"id":"2512.04220","title":"On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement","created":"2025-12-03","cited_by_count":15,"area":"lr"},{"id":"2506.23508","title":"Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective","created":"2025-06-30","cited_by_count":14,"area":"lr"},{"id":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2603.22117","title":"On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation","created":"2026-03-23","cited_by_count":13,"area":"lr"},{"id":"2505.12504","title":"CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models","created":"2025-05-18","cited_by_count":11,"area":"lr"},{"id":"2510.03669","title":"Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning","created":"2025-10-04","cited_by_count":10,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2509.20868","title":"StyleBench: Evaluating thinking styles in Large Language Models","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2505.17988","title":"Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning","created":"2025-05-23","cited_by_count":3,"area":"lr"},{"id":"2603.01683","title":"Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2609.20807","title":"Score Centering Stabilizes Off-policy Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"lr"},{"id":"2601.04670","title":"Learning Dynamics in RL Post-Training for Language Models","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2604.15705","title":"Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning","created":"2026-04-17","cited_by_count":2,"area":"lr"},{"id":"2605.06523","title":"On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2509.06239","title":"Proof2Silicon: Prompt Repair for Verified Code and Hardware Generation via Reinforcement Learning","created":"2025-09-07","cited_by_count":1,"area":"lr"},{"id":"2604.04894","title":"Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2604.26326","title":"Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control","created":"2026-04-29","cited_by_count":1,"area":"lr"},{"id":"2605.07353","title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2606.01558","title":"Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2609.03241","title":"FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.33781","title":"Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}