{"total":19,"rows":[{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"area":"lr"},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65,"area":"lr"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2505.18116","title":"NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning","created":"2025-05-23","cited_by_count":38,"area":"lr"},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2502.14354","title":"Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment","created":"2025-02-20","cited_by_count":16,"area":"lr"},{"id":"2510.03865","title":"Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration","created":"2025-10-04","cited_by_count":7,"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":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"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":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2603.16157","title":"DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2508.10164","title":"Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization","created":"2025-08-13","cited_by_count":3,"area":"lr"},{"id":"2605.06139","title":"Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2604.15705","title":"Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning","created":"2026-04-17","cited_by_count":2,"area":"lr"},{"id":"2605.11726","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","created":"2026-05-12","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":"2607.10481","title":"ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples","created":"2026-07-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}