{"total":34,"rows":[{"id":"2603.19835","title":"FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization","created":"2026-03-20","cited_by_count":25,"area":"lr"},{"id":"2512.21625","title":"Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards","created":"2025-12-25","cited_by_count":19,"area":"lr"},{"id":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2601.03715","title":"R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification","created":"2026-01-07","cited_by_count":12,"area":"lr"},{"id":"2602.17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2511.20718","title":"Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization","created":"2025-11-25","cited_by_count":9,"area":"lr"},{"id":"2602.15620","title":"STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens","created":"2026-02-17","cited_by_count":9,"area":"lr"},{"id":"2512.19126","title":"AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards","created":"2025-12-22","cited_by_count":7,"area":"lr"},{"id":"2601.22718","title":"A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"id":"2605.21125","title":"Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation","created":"2026-05-20","cited_by_count":7,"area":"lr"},{"id":"2601.07036","title":"Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2603.14389","title":"From $\\log \\pi$ to $\\pi$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2603.28204","title":"ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models","created":"2026-03-30","cited_by_count":6,"area":"lr"},{"id":"2602.02150","title":"ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2602.06453","title":"On the Plasticity and Stability for Post-Training Large Language Models","created":"2026-02-06","cited_by_count":4,"area":"lr"},{"id":"2602.04620","title":"QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2604.16918","title":"Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning","created":"2026-04-18","cited_by_count":3,"area":"lr"},{"id":"2606.19236","title":"STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2606.31575","title":"Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index","created":"2026-06-30","cited_by_count":3,"area":"lr"},{"id":"2602.02192","title":"ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2606.04560","title":"Rollout-Level Advantage-Prioritized Experience Replay for GRPO","created":"2026-06-03","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":"2605.06650","title":"Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.08283","title":"HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.22703","title":"Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2606.00755","title":"Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2607.21013","title":"EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2601.03286","title":"HyperCLOVA X 32B Think","created":"2026-01-03","cited_by_count":0,"area":"lr"},{"id":"2601.04731","title":"Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models","created":"2026-01-08","cited_by_count":0,"area":"lr"},{"id":"2606.17735","title":"Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2607.03126","title":"ACPO: Asymmetric Credit Policy Optimization via Mode-Local Entropy Surrogate","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2610.01896","title":"Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02039","title":"CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}