{"list":"other","total":55,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344},{"id":"1803.00942","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling","created":"2018-03-02","cited_by_count":328},{"id":"2506.14245","title":"Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs","created":"2025-06-17","cited_by_count":289},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236},{"id":"2410.01560","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","created":"2024-10-02","cited_by_count":200},{"id":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194},{"id":"2504.07912","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","created":"2025-04-10","cited_by_count":129},{"id":"2506.20512","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","created":"2025-06-25","cited_by_count":113},{"id":"2406.08446","title":"OLMES: A Standard for Language Model Evaluations","created":"2024-06-12","cited_by_count":106},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91},{"id":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90},{"id":"2412.15287","title":"Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models","created":"2024-12-18","cited_by_count":89},{"id":"2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","created":"2025-10-16","cited_by_count":89},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84},{"id":"2506.19767","title":"SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning","created":"2025-06-24","cited_by_count":84},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83},{"id":"2506.02355","title":"Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening","created":"2025-06-03","cited_by_count":80},{"id":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70},{"id":"2512.07783","title":"On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models","created":"2025-12-08","cited_by_count":69},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60},{"id":"2503.19206","title":"Overtrained Language Models Are Harder to Fine-Tune","created":"2025-03-24","cited_by_count":58},{"id":"2505.23433","title":"Diversity-Aware Policy Optimization for Large Language Model Reasoning","created":"2025-05-29","cited_by_count":41},{"id":"2502.01968","title":"Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning","created":"2025-02-04","cited_by_count":39},{"id":"2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","created":"2025-07-17","cited_by_count":38},{"id":"2503.07453","title":"Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration","created":"2025-03-10","cited_by_count":36},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31},{"id":"2510.15020","title":"The Coverage Principle: How Pre-Training Enables Post-Training","created":"2025-10-16","cited_by_count":30},{"id":"2502.07154","title":"Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning","created":"2025-02-11","cited_by_count":29},{"id":"2507.00885","title":"Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check","created":"2025-07-01","cited_by_count":29},{"id":"2510.01624","title":"Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead","created":"2025-10-02","cited_by_count":28},{"id":"2406.10670","title":"CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training","created":"2024-06-15","cited_by_count":20},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16},{"id":"2603.16127","title":"Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning","created":"2026-03-17","cited_by_count":13},{"id":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10},{"id":"2605.02105","title":"Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting","created":"2026-05-04","cited_by_count":10},{"id":"2602.02244","title":"Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models","created":"2026-02-02","cited_by_count":9},{"id":"2504.12491","title":"Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs?","created":"2025-04-16","cited_by_count":7},{"id":"2602.07464","title":"SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning","created":"2026-02-07","cited_by_count":7},{"id":"2601.07389","title":"On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training","created":"2026-01-12","cited_by_count":6},{"id":"2603.12151","title":"IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL","created":"2026-03-12","cited_by_count":6}],"next_cursor":null}