{"total":76,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106,"area":"lr"},{"id":"2509.01142","title":"Dream-Coder 7B: An Open Diffusion Language Model for Code","created":"2025-09-01","cited_by_count":81,"area":"diffusion"},{"id":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2511.16108","title":"SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent","created":"2025-11-20","cited_by_count":48,"area":"agents"},{"id":"2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","created":"2025-09-29","cited_by_count":42,"area":null},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2509.25300","title":"Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning","created":"2025-09-29","cited_by_count":29,"area":"lr"},{"id":"2507.03112","title":"RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents","created":"2025-07-03","cited_by_count":25,"area":"lr"},{"id":"2511.12344","title":"Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning","created":"2025-11-15","cited_by_count":21,"area":"lr"},{"id":"2507.12428","title":"Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models","created":"2025-07-16","cited_by_count":17,"area":"lr"},{"id":"2510.08439","title":"xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning","created":"2025-10-09","cited_by_count":17,"area":null},{"id":"2510.24431","title":"MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation","created":"2025-10-28","cited_by_count":17,"area":null},{"id":"2509.24203","title":"Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2510.26374","title":"BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning","created":"2025-10-30","cited_by_count":14,"area":"alignment"},{"id":"2508.12680","title":"Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation","created":"2025-08-18","cited_by_count":13,"area":"lr"},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2601.14243","title":"Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2510.08325","title":"Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries","created":"2025-10-09","cited_by_count":9,"area":"lr"},{"id":"2604.08865","title":"SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks","created":"2026-04-10","cited_by_count":9,"area":"lr"},{"id":"2509.23657","title":"Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2510.26143","title":"Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math","created":"2025-10-30","cited_by_count":8,"area":"lr"},{"id":"2512.24063","title":"How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns","created":"2025-12-30","cited_by_count":8,"area":"lr"},{"id":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2510.11184","title":"Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2601.18217","title":"Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents","created":"2026-01-26","cited_by_count":6,"area":"agents"},{"id":"2603.12151","title":"IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL","created":"2026-03-12","cited_by_count":6,"area":null},{"id":"2510.25528","title":"Zero Reinforcement Learning Towards General Domains","created":"2025-10-29","cited_by_count":5,"area":"lr"},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2606.25178","title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2609.05295","title":"RISE: Recursive Improvement via Self-Extrapolating Policy Distillation","created":"2026-09-04","cited_by_count":5,"area":"distill"},{"id":"2512.10691","title":"Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning","created":"2025-12-11","cited_by_count":4,"area":"mllm"},{"id":"2601.02648","title":"Prioritized Replay for RL Post-training","created":"2026-01-06","cited_by_count":4,"area":null},{"id":"2601.23058","title":"From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning","created":"2026-01-30","cited_by_count":4,"area":"lr"},{"id":"2602.03978","title":"Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2603.12011","title":"Can RL Improve Generalization of LLM Agents? An Empirical Study","created":"2026-03-12","cited_by_count":4,"area":"agents"},{"id":"2606.20008","title":"VIMPO: Value-Implicit Policy Optimization for LLMs","created":"2026-06-18","cited_by_count":4,"area":"lr"},{"id":"2507.20150","title":"The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models","created":"2025-07-27","cited_by_count":3,"area":"lr"},{"id":"2510.10168","title":"Concise Reasoning in the Lens of Lagrangian Optimization","created":"2025-10-11","cited_by_count":3,"area":"lr"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2601.14560","title":"Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2603.11193","title":"DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2603.19470","title":"Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2604.09748","title":"Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward","created":"2026-04-10","cited_by_count":3,"area":"lr"},{"id":"2511.23476","title":"Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction","created":"2025-11-28","cited_by_count":2,"area":"wm"},{"id":"2604.18574","title":"When Can LLMs Learn to Reason with Weak Supervision?","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2607.08940","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2608.09217","title":"Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training","created":"2026-08-10","cited_by_count":2,"area":"lr"},{"id":"2510.04089","title":"SPOGW: a Score-based Preference Optimization method via Group-Wise comparison for workflows","created":"2025-10-05","cited_by_count":1,"area":"agents"},{"id":"2512.11463","title":"Motif-2-12.7B-Reasoning: A Practitioner's Guide to RL Training Recipes","created":"2025-12-11","cited_by_count":1,"area":"lr"},{"id":"2602.03073","title":"TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT","created":"2026-02-03","cited_by_count":1,"area":"alignment"},{"id":"2602.11217","title":"The Magic Correlations: Understanding Knowledge Transfer from Pretraining to Supervised Fine-Tuning","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.05383","title":"Towards Effective In-context Cross-domain Knowledge Transfer via Domain-invariant-neurons-based Retrieval","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2607.16204","title":"Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL","created":"2026-05-07","cited_by_count":1,"area":"wm"},{"id":"2609.06469","title":"One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control","created":"2026-09-06","cited_by_count":1,"area":"lr"},{"id":"2510.14406","title":"IMAGINE: Integrating Multi-Agent System into One Model for Complex Reasoning and Planning","created":"2025-10-16","cited_by_count":0,"area":"lr"},{"id":"2602.08344","title":"OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2604.08477","title":"SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2606.00609","title":"CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.17735","title":"Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2606.26917","title":"GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.01804","title":"LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.05139","title":"Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.08224","title":"Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.18574","title":"Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2609.26355","title":"PACT: From Credit Assignment to Critic Alignment","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.00979","title":"RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04158","title":"How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}