{"total":14,"rows":[{"id":"2508.11356","title":"ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism","created":"2025-08-15","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":"2509.25849","title":"Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation","created":"2025-09-30","cited_by_count":22,"area":null},{"id":"2603.02216","title":"ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2606.26453","title":"Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization","created":"2026-06-24","cited_by_count":4,"area":null},{"id":"2604.14564","title":"MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2608.24300","title":"Contrastive Branch Policy Optimization","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2604.14518","title":"Mind DeepResearch Technical Report","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.08315","title":"Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias","created":"2026-05-08","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},{"id":"2608.01804","title":"LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.36864","title":"Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40035","title":"OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03372","title":"SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}