{"total":55,"rows":[{"id":"2602.15763","title":"GLM-5: from Vibe Coding to Agentic Engineering","created":"2026-02-17","cited_by_count":587,"area":"agents"},{"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":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2602.08676","title":"LLaDA2.1: Speeding Up Text Diffusion via Token Editing","created":"2026-02-09","cited_by_count":54,"area":"diffusion"},{"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":"2602.09082","title":"UI-Venus-1.5 Technical Report","created":"2026-02-09","cited_by_count":41,"area":"agents"},{"id":"2604.12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37,"area":"lr"},{"id":"2607.07508","title":"Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning","created":"2026-07-08","cited_by_count":37,"area":"agents"},{"id":"2603.25040","title":"Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale","created":"2026-03-26","cited_by_count":29,"area":null},{"id":"2603.19835","title":"FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization","created":"2026-03-20","cited_by_count":25,"area":"lr"},{"id":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2603.06743","title":"Stabilizing Reinforcement Learning for Diffusion Language Models","created":"2026-03-06","cited_by_count":10,"area":"lr"},{"id":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2605.19577","title":"GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment","created":"2026-05-19","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.15079","title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2606.26650","title":"CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs","created":"2026-06-25","cited_by_count":6,"area":null},{"id":"2602.06107","title":"Jackpot: Optimal Budgeted Rejection Sampling for Extreme Actor-Policy Mismatch Reinforcement Learning","created":"2026-02-05","cited_by_count":5,"area":"lr"},{"id":"2605.12070","title":"Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction","created":"2026-05-12","cited_by_count":5,"area":"agents"},{"id":"2606.09821","title":"Rethinking the Divergence Regularization in LLM RL","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2609.02998","title":"Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation","created":"2026-09-02","cited_by_count":5,"area":"distill"},{"id":"2605.18548","title":"STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics","created":"2026-05-18","cited_by_count":4,"area":"agents"},{"id":"2603.21877","title":"P^2O: Joint Policy and Prompt Optimization","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2606.03070","title":"ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2609.20807","title":"Score Centering Stabilizes Off-policy Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"lr"},{"id":"2512.07710","title":"Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE","created":"2025-12-08","cited_by_count":2,"area":"lr"},{"id":"2512.16248","title":"Sigma-MoE-Tiny Technical Report","created":"2025-12-18","cited_by_count":2,"area":"moe"},{"id":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2607.04728","title":"Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment","created":"2026-07-06","cited_by_count":2,"area":"alignment"},{"id":"2609.00028","title":"UI-Venus-2 Technical Report","created":"2026-08-27","cited_by_count":2,"area":"agents"},{"id":"2604.06159","title":"Target Policy Optimization","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.13779","title":"MinT: Managed Infrastructure for Training and Serving Millions of LLMs","created":"2026-05-13","cited_by_count":1,"area":"moe"},{"id":"2605.20865","title":"Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2608.09819","title":"Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2603.14463","title":"An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2604.16259","title":"Beyond Distribution Sharpening: The Importance of Task Rewards","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2604.19147","title":"Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2606.08779","title":"Reformulate LLM Reinforcement Learning for Efficient Training under Black-box Discrepancy","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2607.10848","title":"Predictive Divergence Masks for LLM RL","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.12395","title":"Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2607.22186","title":"Deconstructing Off-Policy Ratios: Entropy-Normalized Trust Regions for Asynchronous Reinforcement Learning","created":"2026-07-24","cited_by_count":0,"area":"deeprl"},{"id":"2608.09119","title":"Motif 3: Technical Report","created":"2026-08-10","cited_by_count":0,"area":"moe"},{"id":"2608.24135","title":"Robust Code RL via Faulty-Code-Driven Test case Synthesis and Dense Reward Shaping","created":"2026-08-25","cited_by_count":0,"area":"alignment"},{"id":"2609.03338","title":"SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis","created":"2026-09-03","cited_by_count":0,"area":"agents"},{"id":"2609.09783","title":"BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.15987","title":"Bellman Policy Optimization","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.25773","title":"Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.32444","title":"Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.35378","title":"Multilinguality in Hybrid Attention LLMs","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.37868","title":"Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.02039","title":"CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.13202","title":"S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding","created":"2026-10-09","cited_by_count":0,"area":"inference"}],"next_cursor":null}