{"total":28,"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":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2404.03683","title":"Stream of Search (SoS): Learning to Search in Language","created":"2024-04-01","cited_by_count":145,"area":"lr"},{"id":"2305.06599","title":"Structured Chain-of-Thought Prompting for Code Generation","created":"2023-05-11","cited_by_count":138,"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":"2507.07017","title":"First Return, Entropy-Eliciting Explore","created":"2025-07-09","cited_by_count":45,"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":"2608.19098","title":"Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation","created":"2026-08-19","cited_by_count":18,"area":"lr"},{"id":"2601.09088","title":"Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning","created":"2026-01-14","cited_by_count":17,"area":"lr"},{"id":"2312.14591","title":"Reasons to Reject? Aligning Language Models with Judgments","created":"2023-12-22","cited_by_count":15,"area":"lr"},{"id":"2404.10163","title":"EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning","created":"2024-04-15","cited_by_count":8,"area":"lr"},{"id":"2504.10187","title":"DeepTrans: Deep Reasoning Translation via Reinforcement Learning","created":"2025-04-14","cited_by_count":8,"area":"lr"},{"id":"2605.19433","title":"Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2605.28396","title":"ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation","created":"2026-05-27","cited_by_count":5,"area":"lr"},{"id":"2601.17982","title":"SD-E$^2$: Semantic Exploration for Reasoning Under Token Budgets","created":"2026-01-25","cited_by_count":3,"area":"lr"},{"id":"2605.12227","title":"A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2508.15766","title":"Discovering Hidden Algebraic Structures via Transformers with Rank-Aware Beam GRPO","created":"2025-08-21","cited_by_count":1,"area":"lr"},{"id":"2606.21884","title":"A Verifiable Search Is Not a Learnable Chain-of-Thought","created":"2026-06-20","cited_by_count":1,"area":"lr"},{"id":"2605.01399","title":"Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning","created":"2026-05-02","cited_by_count":0,"area":"lr"},{"id":"2606.22766","title":"READ More than What You See: Reinforcement Learning for Accurate and Coherent Audio Description Generations","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.01170","title":"Diffusion-GR2: Diffusion Generative Reasoning Re-ranker","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2607.02757","title":"Reinforcement Learning for Data-Efficient Code-Switched ASR","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.14333","title":"SD-MAR: Multi-image Analytical Reasoning via Synthetic Data and Reinforcement Learning","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2608.14685","title":"Rethinking Reverse KL as Adaptive Entropy Distillation","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.22785","title":"OmicSync: Reliability-Aware Spatial Multi-Omics Clustering with Evidence-Constrained LLM Reasoning","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2608.28733","title":"Generation of High-Level Concepts in 3D Scene Graphs via Autoregressive Diffusion","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.33970","title":"On the Token Value Inequality in Efficient Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.18861","title":"Hybrid Reasoning Agents","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}