{"total":101,"rows":[{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2511.07317","title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","created":"2025-11-10","cited_by_count":50,"area":null},{"id":"2601.18779","title":"POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration","created":"2026-01-26","cited_by_count":42,"area":"lr"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37,"area":"lr"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"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":"2605.11739","title":"Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation","created":"2026-05-12","cited_by_count":19,"area":"distill"},{"id":"2602.04663","title":"Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design","created":"2026-02-04","cited_by_count":17,"area":"lr"},{"id":"2605.28014","title":"ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains","created":"2026-05-27","cited_by_count":17,"area":"lr"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2605.10194","title":"STEPS: Selective On-Policy Self-Distillation for Reasoning","created":"2026-05-11","cited_by_count":16,"area":"distill"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2602.21534","title":"ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning","created":"2026-02-25","cited_by_count":13,"area":"agents"},{"id":"2601.19280","title":"Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning","created":"2026-01-27","cited_by_count":12,"area":"lr"},{"id":"2510.23049","title":"Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients","created":"2025-10-27","cited_by_count":11,"area":"lr"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","cited_by_count":11,"area":"lr"},{"id":"2601.22975","title":"Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2602.19362","title":"LLMs Can Learn to Reason Via Off-Policy RL","created":"2026-02-22","cited_by_count":10,"area":"lr"},{"id":"2604.20209","title":"Scaling Self-Play with Self-Guidance","created":"2026-04-22","cited_by_count":10,"area":"synth"},{"id":"2603.21177","title":"Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts","created":"2026-03-22","cited_by_count":8,"area":"lr"},{"id":"2605.08956","title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","created":"2026-05-09","cited_by_count":8,"area":"agents"},{"id":"2602.03839","title":"Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2603.12151","title":"IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL","created":"2026-03-12","cited_by_count":6,"area":null},{"id":"2605.02572","title":"On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length","created":"2026-05-04","cited_by_count":6,"area":null},{"id":"2605.12484","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"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":"2602.14697","title":"Evolutionary System Prompt Learning for Reinforcement Learning in LLMs","created":"2026-02-16","cited_by_count":5,"area":"agents"},{"id":"2607.16097","title":"Understanding Reasoning from Pretraining to Post-Training","created":"2026-07-17","cited_by_count":5,"area":"lr"},{"id":"2512.16144","title":"INTELLECT-3: Technical Report","created":"2025-12-18","cited_by_count":4,"area":"lr"},{"id":"2602.10231","title":"Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2602.14868","title":"Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning","created":"2026-02-16","cited_by_count":4,"area":"lr"},{"id":"2602.22124","title":"SWE-Prot\\'eg\\'e: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents","created":"2026-02-25","cited_by_count":4,"area":"agents"},{"id":"2603.18325","title":"Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum","created":"2026-03-18","cited_by_count":4,"area":"lr"},{"id":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2605.06761","title":"Weblica: Scalable and Reproducible Training Environments for Visual Web Agents","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2512.20061","title":"Scaling Reinforcement Learning for Content Moderation with Large Language Models","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2601.20221","title":"Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2605.04077","title":"Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO","created":"2026-04-14","cited_by_count":3,"area":"lr"},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2606.24143","title":"AsyncOPD: How Stale Can On-Policy Distillation Be?","created":"2026-06-23","cited_by_count":3,"area":"distill"},{"id":"2609.20807","title":"Score Centering Stabilizes Off-policy Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"lr"},{"id":"2512.05033","title":"Arbitrage: Efficient Reasoning via Advantage-Aware Speculation","created":"2025-12-04","cited_by_count":2,"area":"lr"},{"id":"2512.11470","title":"Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning","created":"2025-12-12","cited_by_count":2,"area":"lr"},{"id":"2601.01739","title":"K-EXAONE Technical Report","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2602.06869","title":"Uncovering Cross-Objective Interference in Multi-Objective Alignment","created":"2026-02-06","cited_by_count":2,"area":"alignment"},{"id":"2602.10300","title":"Configuration-to-Performance Scaling Law with Neural Ansatz","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2602.11639","title":"PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2603.15798","title":"CUBE: A Standard for Unifying Agent Benchmarks","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2606.02218","title":"Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing","created":"2026-06-01","cited_by_count":2,"area":"lr"},{"id":"2607.01083","title":"Staleness-Learning Rate Scaling Laws for Asynchronous RLHF","created":"2026-07-01","cited_by_count":2,"area":"alignment"},{"id":"2607.13389","title":"Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2511.04439","title":"CoRPO: Adding a Correctness Bias to GRPO Improves Generalization","created":"2025-11-06","cited_by_count":1,"area":"lr"},{"id":"2601.05633","title":"GIFT: Games as Informal Training for Generalizable LLMs","created":"2026-01-09","cited_by_count":1,"area":"lr"},{"id":"2601.23027","title":"Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.07670","title":"Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2604.06159","title":"Target Policy Optimization","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.08690","title":"Skip-Connected Policy Optimization for Implicit Advantage","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.28020","title":"Cost-Aware Learning","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.06638","title":"Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"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":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.03937","title":"Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"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":"2606.16517","title":"How Post-Training Shapes Biological Reasoning Models","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2609.13443","title":"Learning to Solve Hard Problems in RL for LLMs by Never Giving Up","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2609.34645","title":"Nereus: Adaptive Parallelism for LLM Post-Training","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2610.10447","title":"A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching","created":"2026-10-07","cited_by_count":1,"area":"distill"},{"id":"2601.14599","title":"Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective","created":"2026-01-21","cited_by_count":0,"area":"lr"},{"id":"2601.14695","title":"CoScale-RL: Efficient Post-Training by Co-Scaling Data and Computation","created":"2026-01-21","cited_by_count":0,"area":"lr"},{"id":"2601.22532","title":"Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.00927","title":"Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2602.11596","title":"MAPLE: Modality-Aware Post-training and Learning Ecosystem","created":"2026-02-12","cited_by_count":0,"area":"mllm"},{"id":"2603.28507","title":"Continued AI Scaling Requires Repeated Efficiency Doublings","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.02007","title":"Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2604.14969","title":"Discovering Novel LLM Experts via Task-Capability Coevolution","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.16259","title":"Beyond Distribution Sharpening: The Importance of Task Rewards","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2604.18381","title":"Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.28109","title":"Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.11431","title":"Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.11634","title":"Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.19750","title":"Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2607.01490","title":"Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2609.00444","title":"Group Adaptive Clipping Policy Optimization","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.15987","title":"Bellman Policy Optimization","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.16648","title":"GrowMTP: Can RL Grow Its Own Draft Head?","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.27166","title":"Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.32722","title":"Scaling Properties of Same-Family On-Policy Distillation","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.39247","title":"Trust the Critic More","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02828","title":"FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04158","title":"How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.06204","title":"Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.16866","title":"Efficient Resource-Shiftable RL Post-training with Generative Rewards","created":"2026-10-12","cited_by_count":0,"area":"alignment"},{"id":"2610.18853","title":"Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":"100"}