{"total":17,"rows":[{"id":"2609.11042","title":"T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks","created":"2026-09-10","cited_by_count":7,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2606.09821","title":"Rethinking the Divergence Regularization in LLM RL","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2606.18844","title":"Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2608.23566","title":"Best Practice Critic Optimization","created":"2026-08-24","cited_by_count":4,"area":"lr"},{"id":"2606.10968","title":"Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning","created":"2026-06-09","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":"2605.20865","title":"Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2606.13680","title":"Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2608.09271","title":"SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation","created":"2026-08-10","cited_by_count":1,"area":"lr"},{"id":"2607.06987","title":"UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2608.27046","title":"Performance Foundations of Parallel & Distributed Reasoning Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2609.15987","title":"Bellman Policy Optimization","created":"2026-09-14","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"},{"id":"2610.13015","title":"Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.13020","title":"Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}