{"total":57,"rows":[{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350,"area":"lr"},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"area":"lr"},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2410.14803","title":"DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents","created":"2024-10-18","cited_by_count":68,"area":"lr"},{"id":"2402.05808","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","created":"2024-02-08","cited_by_count":65,"area":"lr"},{"id":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","cited_by_count":52,"area":"lr"},{"id":"2507.02841","title":"StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason","created":"2025-07-03","cited_by_count":39,"area":"lr"},{"id":"2502.06533","title":"Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning","created":"2025-02-10","cited_by_count":34,"area":"lr"},{"id":"2505.18454","title":"Hybrid Latent Reasoning via Reinforcement Learning","created":"2025-05-24","cited_by_count":32,"area":"lr"},{"id":"2503.04550","title":"Benchmarking Reasoning Robustness in Large Language Models","created":"2025-03-06","cited_by_count":30,"area":"lr"},{"id":"2509.18521","title":"APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation","created":"2025-09-23","cited_by_count":30,"area":"lr"},{"id":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"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":"2605.07865","title":"KL for a KL: On-Policy Distillation with Control Variate Baseline","created":"2026-05-08","cited_by_count":26,"area":"lr"},{"id":"2505.18573","title":"Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs","created":"2025-05-24","cited_by_count":23,"area":"lr"},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","cited_by_count":19,"area":"lr"},{"id":"2508.03772","title":"GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control","created":"2025-08-05","cited_by_count":18,"area":"lr"},{"id":"2510.06672","title":"XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2410.11689","title":"BlendRL: A Framework for Merging Symbolic and Neural Policy Learning","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2602.19208","title":"How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization","created":"2026-02-22","cited_by_count":14,"area":"lr"},{"id":"2602.19362","title":"LLMs Can Learn to Reason Via Off-Policy RL","created":"2026-02-22","cited_by_count":10,"area":"lr"},{"id":"2310.18127","title":"Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models","created":"2023-10-27","cited_by_count":9,"area":"lr"},{"id":"2411.00773","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","created":"2024-11-01","cited_by_count":8,"area":"lr"},{"id":"2505.17673","title":"Rethinking Agent Design: From Top-Down Workflows to Bottom-Up Skill Evolution","created":"2025-05-23","cited_by_count":6,"area":"lr"},{"id":"2511.03527","title":"Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments","created":"2025-11-05","cited_by_count":6,"area":"lr"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2512.11816","title":"Reinforcement Learning for Latent-Space Thinking in LLMs","created":"2025-11-26","cited_by_count":4,"area":"lr"},{"id":"2604.00304","title":"Asymmetric Actor-Critic for Multi-turn LLM Agents","created":"2026-03-31","cited_by_count":4,"area":"lr"},{"id":"2202.12162","title":"Measuring CLEVRness: Blackbox testing of Visual Reasoning Models","created":"2022-02-24","cited_by_count":3,"area":"lr"},{"id":"2509.23183","title":"ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2605.11491","title":"Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2210.06766","title":"Policy Gradient With Serial Markov Chain Reasoning","created":"2022-10-13","cited_by_count":2,"area":"lr"},{"id":"2511.17852","title":"Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently","created":"2025-11-22","cited_by_count":2,"area":"lr"},{"id":"2512.15089","title":"Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models","created":"2025-12-17","cited_by_count":2,"area":"lr"},{"id":"2606.05597","title":"AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"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":"2507.03018","title":"OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering","created":"2025-07-02","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":"2504.06618","title":"Human-like compositional learning of visually-grounded concepts using synthetic environments","created":"2025-04-09","cited_by_count":0,"area":"lr"},{"id":"2508.08665","title":"Aryabhata: An exam-focused language model for JEE Math","created":"2025-08-12","cited_by_count":0,"area":"lr"},{"id":"2510.21306","title":"PARL: Prompt-based Agents for Reinforcement Learning","created":"2025-10-24","cited_by_count":0,"area":"lr"},{"id":"2604.16259","title":"Beyond Distribution Sharpening: The Importance of Task Rewards","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.22195","title":"Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMs","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.05800","title":"SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter","created":"2026-06-04","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.21626","title":"Discrete Action Space as a Prerequisite for GRPO Convergence in Small-Model Continuous Control","created":"2026-07-07","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"},{"id":"2609.34422","title":"Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36058","title":"ABC: Advantage-Based Control Variates for Reinforcement Learning with Verifiable Rewards","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36742","title":"SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}