{"total":48,"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":"2509.06160","title":"Reverse-Engineered Reasoning for Open-Ended Generation","created":"2025-09-07","cited_by_count":32,"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":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2509.22638","title":"Language Models Can Learn from Verbal Feedback Without Scalar Rewards","created":"2025-09-26","cited_by_count":18,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2512.14051","title":"OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value","created":"2025-12-16","cited_by_count":15,"area":null},{"id":"2507.05195","title":"Train-before-Test Harmonizes Language Model Rankings","created":"2025-07-07","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":"2602.06204","title":"Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2605.29559","title":"LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents","created":"2026-05-28","cited_by_count":8,"area":null},{"id":"2607.06973","title":"Rethinking Multimodal Time-Series Forecasting Evaluation","created":"2026-07-08","cited_by_count":7,"area":null},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2601.09066","title":"Mi:dm 2.0 Korea-centric Bilingual Language Models","created":"2026-01-14","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":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2602.14696","title":"A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2605.23454","title":"ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning","created":"2026-05-22","cited_by_count":4,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2603.08371","title":"Leaderboard Incentives: Model Rankings under Strategic Post-Training","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2509.13624","title":"Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2601.06788","title":"Artificial Entanglement in the Fine-Tuning of Large Language Models","created":"2026-01-11","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.13808","title":"The Culture Funnel: You Can't Align What isn't in the Data","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2608.01735","title":"DAPD: Dual-Anchored Policy Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2508.10409","title":"Dataset Construction for Training LLM to Learn Analog Circuit Knowledge","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2601.06953","title":"X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2603.23562","title":"Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.05426","title":"ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.19877","title":"Super Apriel: One Checkpoint, Many Speeds","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2607.27770","title":"Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold","created":"2026-07-30","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":"2511.18411","title":"SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2603.12875","title":"Test-time RL alignment exposes task familiarity artifacts in LLM benchmarks","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.17614","title":"Characterizing Model-Native Skills","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.01111","title":"When Less is Enough: Efficient Inference via Collaborative Reasoning","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.14217","title":"PreFT: Prefill-only finetuning for efficient inference","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.12883","title":"The Hidden Power of Scaling Factor in LoRA Optimization","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.02118","title":"Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training","created":"2026-07-02","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":"2609.36246","title":"Learning from Teacher Continuations at Student States","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37891","title":"It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39884","title":"OPSRD: On-Policy Self-Role Distillation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05318","title":"Robust Parameter-Efficient LLM Adaptation on Analog Hardware","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.13568","title":"Rationally Linearized MLPs","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}