{"total":77,"rows":[{"id":"2506.20639","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","created":"2025-06-25","cited_by_count":187,"area":"diffusion"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2510.25741","title":"Scaling Latent Reasoning via Looped Language Models","created":"2025-10-29","cited_by_count":165,"area":"lr"},{"id":"2509.09674","title":"SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning","created":"2025-09-11","cited_by_count":151,"area":"vla"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"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,"area":"lr"},{"id":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"id":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2508.07629","title":"Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization","created":"2025-08-11","cited_by_count":39,"area":"lr"},{"id":"2509.07430","title":"The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward","created":"2025-09-09","cited_by_count":37,"area":null},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28,"area":"lr"},{"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,"area":"lr"},{"id":"2510.09719","title":"ICL-Router: In-Context Learned Model Representations for LLM Routing","created":"2025-10-10","cited_by_count":28,"area":null},{"id":"2510.03264","title":"Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data","created":"2025-09-26","cited_by_count":27,"area":"lr"},{"id":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22,"area":"agents"},{"id":"2510.04454","title":"Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2605.07721","title":"Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models","created":"2026-05-08","cited_by_count":14,"area":"inference"},{"id":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2507.07562","title":"The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs","created":"2025-07-10","cited_by_count":12,"area":"lr"},{"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":"2508.09883","title":"Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning","created":"2025-08-13","cited_by_count":11,"area":"lr"},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","cited_by_count":11,"area":"agents"},{"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,"area":"lr"},{"id":"2510.03988","title":"The Signal is in the Steps: Local Scoring for Reasoning Data Selection","created":"2025-10-05","cited_by_count":8,"area":"distill"},{"id":"2510.27072","title":"Towards Understanding Self-play for LLM Reasoning","created":"2025-10-31","cited_by_count":8,"area":"lr"},{"id":"2602.11779","title":"Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement Learning","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2604.14164","title":"How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2510.22543","title":"FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning","created":"2025-10-26","cited_by_count":7,"area":"lr"},{"id":"2509.21070","title":"ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning","created":"2025-09-25","cited_by_count":6,"area":"lr"},{"id":"2512.20908","title":"Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation","created":"2025-12-24","cited_by_count":6,"area":"lr"},{"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,"area":"lr"},{"id":"2602.13935","title":"Statistical Early Stopping for Reasoning Models","created":"2026-02-15","cited_by_count":6,"area":"lr"},{"id":"2608.04001","title":"Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility","created":"2026-08-04","cited_by_count":6,"area":"lr"},{"id":"2508.11818","title":"Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understanding","created":"2025-08-15","cited_by_count":5,"area":"lr"},{"id":"2602.01203","title":"Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse","created":"2026-02-01","cited_by_count":5,"area":"moe"},{"id":"2509.20186","title":"Thinking Augmented Pre-training","created":"2025-09-24","cited_by_count":4,"area":"lr"},{"id":"2601.01562","title":"Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement","created":"2026-01-04","cited_by_count":4,"area":"lr"},{"id":"2602.14012","title":"From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection","created":"2026-02-15","cited_by_count":4,"area":"alignment"},{"id":"2605.18643","title":"Post-Trained MoE Can Skip Half Experts via Self-Distillation","created":"2026-05-18","cited_by_count":4,"area":"moe"},{"id":"2605.25507","title":"Credit Assignment with Resets in Language Model Reasoning","created":"2026-05-25","cited_by_count":4,"area":"lr"},{"id":"2510.02227","title":"More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration","created":"2025-10-02","cited_by_count":3,"area":"lr"},{"id":"2602.18600","title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","created":"2026-02-20","cited_by_count":3,"area":"lr"},{"id":"2605.18864","title":"SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs","created":"2026-05-15","cited_by_count":3,"area":"lr"},{"id":"2510.17045","title":"Video Reasoning without Training","created":"2025-10-19","cited_by_count":2,"area":"lr"},{"id":"2601.09233","title":"GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2603.16206","title":"Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical Reasoning","created":"2026-03-17","cited_by_count":2,"area":"lr"},{"id":"2605.08862","title":"BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.28003","title":"ResearchMath-14K: Scaling Research-Level Mathematics via Agents","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2508.10530","title":"Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?","created":"2025-08-14","cited_by_count":1,"area":"alignment"},{"id":"2508.14765","title":"PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning","created":"2025-08-20","cited_by_count":1,"area":"lr"},{"id":"2512.12487","title":"More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language Models","created":"2025-12-13","cited_by_count":1,"area":"lr"},{"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":"2602.17993","title":"Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers","created":"2026-02-20","cited_by_count":1,"area":"lr"},{"id":"2603.10960","title":"Ranking Reasoning LLMs under Test-Time Scaling","created":"2026-03-11","cited_by_count":1,"area":"lr"},{"id":"2605.29303","title":"Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2607.09424","title":"A Sovereign, Open-Source Foundation Model for German and English","created":"2026-07-10","cited_by_count":1,"area":"moe"},{"id":"2608.13721","title":"Capacity-Dependent Effects of Data Selection for Reasoning","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2508.08665","title":"Aryabhata: An exam-focused language model for JEE Math","created":"2025-08-12","cited_by_count":0,"area":"lr"},{"id":"2508.13382","title":"Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis","created":"2025-08-18","cited_by_count":0,"area":"lr"},{"id":"2509.25455","title":"PIPer: On-Device Environment Setup via Online Reinforcement Learning","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2602.02554","title":"BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation","created":"2026-01-30","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":"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":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.13517","title":"DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.08404","title":"Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.24066","title":"Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.31571","title":"Strategically Diverse Sampling for Self-Training","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.35699","title":"Distillation Defenses Easily Break After Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.17824","title":"Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}