{"total":33,"rows":[{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130,"area":null},{"id":"2602.21193","title":"On Data Engineering for Scaling LLM Terminal Capabilities","created":"2026-02-24","cited_by_count":43,"area":null},{"id":"2509.24663","title":"InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation","created":"2025-09-29","cited_by_count":32,"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":"2509.04185","title":"Set Block Decoding is a Language Model Inference Accelerator","created":"2025-09-04","cited_by_count":23,"area":null},{"id":"2511.15248","title":"EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control","created":"2025-11-19","cited_by_count":13,"area":null},{"id":"2512.23165","title":"Evaluating Parameter Efficient Methods for RLVR","created":"2025-12-29","cited_by_count":12,"area":null},{"id":"2601.06395","title":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","created":"2026-01-10","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":"2607.15178","title":"T^2MLR: Transformer with Temporal Middle-Layer Recurrence","created":"2026-07-16","cited_by_count":7,"area":null},{"id":"2512.08894","title":"Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training","created":"2025-12-09","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":"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":"2603.18806","title":"dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2604.03253","title":"Self-Execution Simulation Improves Coding Models","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2604.04898","title":"QED-Nano: Teaching a Tiny Model to Prove Hard Theorems","created":"2026-04-06","cited_by_count":3,"area":null},{"id":"2605.28751","title":"Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2506.19140","title":"Command-V: Pasting LLM Behaviors via Activation Profiles","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2601.06106","title":"Judge Model for Large-scale Multimodality Benchmarks","created":"2026-01-03","cited_by_count":1,"area":null},{"id":"2601.22108","title":"Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2608.13721","title":"Capacity-Dependent Effects of Data Selection for Reasoning","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.13966","title":"QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction","created":"2026-08-14","cited_by_count":1,"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":"2604.19087","title":"OLLM: Options-based Large Language Models","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.12906","title":"Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning","created":"2026-05-13","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":"2606.07527","title":"Post-training is (Massive) Supervised Learning","created":"2026-04-20","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":"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":"2608.28591","title":"Expert-validated STEM QA","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2609.33271","title":"Next Thoughts Are Distributions: Generative Autoregressive Reasoning in the Latent Space","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.19685","title":"Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}