{"total":69,"rows":[{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2602.10885","title":"Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics","created":"2026-02-11","cited_by_count":26,"area":"lr"},{"id":"2601.15165","title":"The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models","created":"2026-01-21","cited_by_count":18,"area":"lr"},{"id":"2601.18418","title":"daVinci-Dev: Agent-native Mid-training for Software Engineering","created":"2026-01-26","cited_by_count":18,"area":"agents"},{"id":"2602.14093","title":"GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training","created":"2026-02-15","cited_by_count":18,"area":"agents"},{"id":"2605.10781","title":"Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR","created":"2026-05-11","cited_by_count":15,"area":"lr"},{"id":"2601.03715","title":"R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification","created":"2026-01-07","cited_by_count":12,"area":"lr"},{"id":"2602.03773","title":"Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2603.01223","title":"Learn Hard Problems During RL with Reference Guided Fine-tuning","created":"2026-03-01","cited_by_count":12,"area":"lr"},{"id":"2606.26091","title":"On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity","created":"2026-06-24","cited_by_count":10,"area":"distill"},{"id":"2601.04436","title":"Learning to Simulate Human Dialogue","created":"2026-01-07","cited_by_count":9,"area":null},{"id":"2602.09463","title":"SpotAgent: Grounding Visual Geo-localization in Large Vision-Language Models through Agentic Reasoning","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2512.23966","title":"Efficient Context Scaling with LongCat ZigZag Attention","created":"2025-12-30","cited_by_count":6,"area":null},{"id":"2601.15158","title":"Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data","created":"2026-01-21","cited_by_count":6,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2601.21742","title":"Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems","created":"2026-01-29","cited_by_count":6,"area":"agents"},{"id":"2602.10356","title":"Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents","created":"2026-02-10","cited_by_count":6,"area":"agents"},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2602.01204","title":"ASTER: Agentic Scaling with Tool-integrated Extended Reasoning","created":"2026-02-01","cited_by_count":5,"area":"lr"},{"id":"2602.01992","title":"Emergent Analogical Reasoning in Transformers","created":"2026-02-02","cited_by_count":5,"area":"lr"},{"id":"2604.02345","title":"UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics","created":"2026-02-11","cited_by_count":5,"area":"agents"},{"id":"2604.08905","title":"StaRPO: Stability-Augmented Reinforcement Policy Optimization","created":"2026-04-10","cited_by_count":5,"area":"lr"},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5,"area":"lr"},{"id":"2607.16097","title":"Understanding Reasoning from Pretraining to Post-Training","created":"2026-07-17","cited_by_count":5,"area":"lr"},{"id":"2602.01523","title":"A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2604.01702","title":"On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning","created":"2026-04-02","cited_by_count":4,"area":"lr"},{"id":"2605.07153","title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2605.30451","title":"VeriGate: Verifier-Gated Step-Level Supervision for GRPO","created":"2026-05-28","cited_by_count":4,"area":"lr"},{"id":"2512.22322","title":"SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents","created":"2025-12-26","cited_by_count":3,"area":"agents"},{"id":"2602.09276","title":"Effective Reasoning Chains Reduce Intrinsic Dimensionality","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2603.01301","title":"When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains","created":"2026-03-01","cited_by_count":3,"area":"lr"},{"id":"2604.14142","title":"From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2605.06241","title":"Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2605.16787","title":"The Unlearnability Phenomenon in RLVR for Language Models","created":"2026-05-16","cited_by_count":3,"area":"lr"},{"id":"2607.24720","title":"The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation","created":"2026-07-27","cited_by_count":3,"area":"wm"},{"id":"2601.03969","title":"Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models","created":"2026-01-07","cited_by_count":2,"area":"lr"},{"id":"2601.07022","title":"Solar Open Technical Report","created":"2026-01-11","cited_by_count":2,"area":"moe"},{"id":"2603.02208","title":"Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2604.18574","title":"When Can LLMs Learn to Reason with Weak Supervision?","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2604.22779","title":"KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2605.28008","title":"Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.06096","title":"OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2606.13125","title":"Select and Improve: Understanding the Mechanics of Post-Training for Reasoning","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2607.09492","title":"Multimodal Reward Hacking in Reinforcement Learning","created":"2026-07-10","cited_by_count":2,"area":"mllm"},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2602.03084","title":"AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2603.19987","title":"Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States","created":"2026-03-20","cited_by_count":1,"area":"alignment"},{"id":"2605.08472","title":"Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models","created":"2026-05-08","cited_by_count":1,"area":"synth"},{"id":"2605.20285","title":"Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2605.31058","title":"Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.04272","title":"RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.13760","title":"Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models","created":"2026-08-13","cited_by_count":1,"area":"lr"},{"id":"2602.00770","title":"Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2602.01660","title":"CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2603.19294","title":"Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2605.24331","title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2606.17024","title":"ExpRL: Exploratory RL for LLM Mid-Training","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2606.27369","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.13545","title":"LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.21325","title":"Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.01532","title":"Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.09081","title":"Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.35954","title":"ROSS: Relearning from Self-Generated Rollouts through Selective Supervision","created":"2026-09-28","cited_by_count":0,"area":"synth"},{"id":"2610.01509","title":"Sharpening Tax in Post-Training","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04978","title":"What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05872","title":"Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning","created":"2026-10-05","cited_by_count":0,"area":"distill"}],"next_cursor":null}