{"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":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208,"area":"lr"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2601.03192","title":"MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory","created":"2026-01-06","cited_by_count":129,"area":"lr"},{"id":"2509.03646","title":"Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning","created":"2025-09-03","cited_by_count":42,"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":"2505.18116","title":"NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning","created":"2025-05-23","cited_by_count":38,"area":"lr"},{"id":"2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","created":"2025-07-17","cited_by_count":38,"area":"lr"},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34,"area":"lr"},{"id":"2602.01381","title":"On the Power of (Approximate) Reward Models for Inference-Time Scaling","created":"2026-02-01","cited_by_count":7,"area":"lr"},{"id":"2606.15576","title":"Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning","created":"2026-06-14","cited_by_count":7,"area":"lr"},{"id":"2605.19461","title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","created":"2026-05-19","cited_by_count":6,"area":"lr"},{"id":"2605.04542","title":"Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation","created":"2026-05-06","cited_by_count":5,"area":"lr"},{"id":"2510.05825","title":"Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling","created":"2025-10-07","cited_by_count":4,"area":"lr"},{"id":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","cited_by_count":4,"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":"2210.06766","title":"Policy Gradient With Serial Markov Chain Reasoning","created":"2022-10-13","cited_by_count":2,"area":"lr"},{"id":"2509.21170","title":"Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought Approach","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2605.08978","title":"Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2507.13710","title":"SoftPipe: A Soft-Guided Reinforcement Learning Framework for Automated Data Preparation","created":"2025-07-18","cited_by_count":0,"area":"lr"},{"id":"2507.16473","title":"Learning Temporal Abstractions via Variational Homomorphisms in Option-Induced Abstract MDPs","created":"2025-07-22","cited_by_count":0,"area":"lr"},{"id":"2512.20169","title":"Learning to Reason in LLMs by Expectation Maximization","created":"2025-12-23","cited_by_count":0,"area":"lr"},{"id":"2604.25907","title":"How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum","created":"2026-04-28","cited_by_count":0,"area":"lr"},{"id":"2609.28385","title":"When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.28625","title":"RLVR landscapes for iterated multiplications can be benign: Insights from spin-glass theory","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.35699","title":"Distillation Defenses Easily Break After Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.03361","title":"Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}