{"total":53,"rows":[{"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":"2509.03493","title":"On Entropy Control in LLM-RL Algorithms","created":"2025-09-03","cited_by_count":40,"area":null},{"id":"2505.13445","title":"Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards","created":"2025-05-19","cited_by_count":38,"area":null},{"id":"2506.21621","title":"The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical Proofs","created":"2025-06-23","cited_by_count":30,"area":null},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"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":"2601.21582","title":"Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves","created":"2026-01-29","cited_by_count":12,"area":null},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2602.12222","title":"Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training","created":"2026-02-12","cited_by_count":11,"area":null},{"id":"2510.05969","title":"Probing the Difficulty Perception Mechanism of Large Language Models","created":"2025-10-07","cited_by_count":8,"area":null},{"id":"2601.10242","title":"Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?","created":"2026-01-15","cited_by_count":8,"area":null},{"id":"2511.11134","title":"GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models","created":"2025-11-14","cited_by_count":6,"area":null},{"id":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2510.26697","title":"The End of Manual Decoding: Towards Truly End-to-End Language Models","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2605.26606","title":"Spend Your Rollouts Where It Counts: Rollout Allocation for Group-Based RL Post-Training","created":"2026-05-26","cited_by_count":5,"area":null},{"id":"2512.01224","title":"CoSineVerifier: Tool-Augmented Answer Verification for Computation-Oriented Scientific Questions","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2601.09733","title":"Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2603.07223","title":"Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2511.21714","title":"GPS: General Per-Sample Prompter","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2601.21414","title":"System 1&2 Synergy via Dynamic Model Interpolation","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2605.30334","title":"Demystifying Data Organization for Enhanced LLM Training","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2607.07674","title":"Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2512.11013","title":"PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2607.04332","title":"On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2511.23310","title":"Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2603.03298","title":"TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.21373","title":"PLR: Plackett-Luce for Reordering In-Context Learning Examples","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2605.26971","title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.14971","title":"FastMix: Fast Data Mixture Optimization via Gradient Descent","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2609.19164","title":"Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.39223","title":"QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2601.13995","title":"From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2601.23048","title":"From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.11510","title":"Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.12160","title":"PubSwap: Public-Data Off-Policy Coordination for Federated RLVR","created":"2026-04-14","cited_by_count":0,"area":null},{"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":"2604.27039","title":"Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.08905","title":"Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.20369","title":"DEL: Digit Entropy Loss for Numerical Learning of Large Language Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.25381","title":"Not only where, But when: Temporal Scheduling for RLVR","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.29424","title":"EntroRouter: Learning Efficient Model Routing via Entropy Regulation","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.07690","title":"Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.26179","title":"Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.14221","title":"MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.22354","title":"SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.29798","title":"R$^2$A: Learning Persona Policies Through Persona Representation Learning and Runtime Alignment","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.36659","title":"On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.36864","title":"Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.14021","title":"CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.14437","title":"From Transfer Probes to Expert Grouping: Evidence from LoRA Post-Training","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.14745","title":"SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}