{"total":16,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"id":"2507.11473","title":"Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety","created":"2025-07-15","cited_by_count":249,"area":"lr"},{"id":"2401.01879","title":"Theoretical guarantees on the best-of-n alignment policy","created":"2024-01-03","cited_by_count":124,"area":"lr"},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93,"area":"lr"},{"id":"2503.19385","title":"Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing","created":"2025-03-25","cited_by_count":38,"area":"lr"},{"id":"2502.19735","title":"R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning","created":"2025-02-27","cited_by_count":21,"area":"lr"},{"id":"2605.03327","title":"DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment","created":"2026-05-05","cited_by_count":7,"area":"lr"},{"id":"2509.20368","title":"LATTS: Locally Adaptive Test-Time Scaling","created":"2025-09-16","cited_by_count":4,"area":"lr"},{"id":"2512.05962","title":"Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2505.17242","title":"Optimal Policy Minimum Bayesian Risk","created":"2025-05-22","cited_by_count":2,"area":"lr"},{"id":"2602.16154","title":"Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution","created":"2026-02-18","cited_by_count":2,"area":"lr"},{"id":"2510.00546","title":"ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding","created":"2025-10-01","cited_by_count":1,"area":"lr"},{"id":"2605.02375","title":"Binary Rewards and Reinforcement Learning: Fundamental Challenges","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2610.02015","title":"On Language Drift during RLVR Post-Training","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.17726","title":"TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}