| 2026-11-17 | 2611.20882 | Accelerate Bench: Evaluating Agents for Application-Level Program Optimization | Bowen Liu et al. | arXiv | 18 | |
| 2026-11-05 | 2611.06518 | EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL | Mingzhe Zheng et al. | arXiv | 25 | |
| 2026-11-05 | 2611.08240 | FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning | Haitao Lin et al. | arXiv | 9 | |
| 2026-10-27 | 2610.36729 | Hy-Nomas: Towards Free-form Interactive World Generation | Qiaoling Chen et al. | arXiv | 122 |  |
| 2026-10-21 | 2610.27435 | Harness Self-Evolution for Long-Horizon Terminal Agents | Ruhan Wang et al. | arXiv | 13 | |
| 2026-10-19 | 2610.23181 | Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning | Heming Zou et al. | arXiv | 53 | |
| 2026-10-14 | 2610.18092 | LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity | Yibo Wang et al. | arXiv | 17 | |
| 2026-10-14 | 2610.04906 | Scaling Verifiable Environments for Long-horizon Work Agents | Jiazheng Zhang et al. | arXiv | 5 | |
| 2026-10-14 | 2609.37377 | Beyond Prompt Count: How Data Shapes Transfer in On-Policy Distillation | Jiaxuan Wang et al. | arXiv | 3 | |
| 2026-10-09 | 2610.06801 | MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers | Jiarui Chen et al. | arXiv | 40 | |
| 2026-10-09 | 2610.12458 | OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning | Zhongyu Yang et al. | arXiv | 15 | |
| 2026-10-09 | 2609.34344 | Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors | Yuchen Cai et al. | arXiv | 4 | |
| 2026-10-06 | 2610.05416 | Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training | Shuyuan Tu et al. | arXiv | 17 | |
| 2026-10-05 | 2610.02826 | Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite | Zongxia Li et al. | arXiv | 42 | |
| 2026-10-02 | 2610.01215 | AutoGUIWorld: Image Generators as Visual World Models for GUI Agent | Cheng Yang et al. | arXiv | 38 | |
| 2026-10-02 | 2609.34621 | Does Native 3D Texture Generation Necessarily Require 3D Assets for Training? | Jiangshan Wang et al. | arXiv | 3 | |
| 2026-09-29 | 2609.35457 | How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining | Lin Chen et al. | arXiv | 61 | |
| 2026-09-25 | 2609.30199 | ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds | Ming Zhang et al. | arXiv | 30 | |
| 2026-09-24 | 2609.27284 | Hunyuan-A13B Technical Report | Tencent Hunyuan Team et al. | arXiv | 21 | |
| 2026-09-14 | 2609.13141 | SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking | Zhiwei Li et al. | arXiv | 68 | |
| 2026-09-10 | 2609.11042 | T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks | Junyao Yang et al. | arXiv | 65 | |
| 2026-09-09 | 2609.08936 | AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing | Ziyang Ma et al. | arXiv | 138 | |
| 2026-09-09 | 2609.08977 | Omni Interaction Agent Technical Report | Orantqing et al. | arXiv | 73 | |
| 2026-09-08 | 2609.03241 | FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience | Zixun Huang et al. | arXiv | 43 | |
| 2026-09-04 | 2609.04128 | Environment Evolution for Terminal Agents | Zhiyuan Fan et al. | arXiv | 10 | |
| 2026-09-02 | 2609.00646 | DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation | Haoyuan Shi et al. | arXiv | 15 | |
| 2026-09-01 | 2608.29252 | Dynamic Important Example Mining for Reinforcement Finetuning | Haoru Tan et al. | arXiv | 5 | |
| 2026-08-26 | 2608.24794 | CAFE: Self-Improving Search Agents Need Co-Evolving Feedback | Boyang Liu et al. | arXiv | 6 | |
| 2026-08-25 | 2608.21833 | GameXpert-Bench: How Far Are Coding Agents from Expert Game Development? | Kun Chen et al. | arXiv | 18 | |
| 2026-08-21 | 2608.20336 | WithEveryone: Unified Planning and Identity Grounding for Group Image Generation | Hengyuan Xu et al. | arXiv | 39 | |
| 2026-08-18 | 2608.15930 | UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations | Zihan Ding et al. | arXiv | 48 | |
| 2026-08-07 | 2608.05248 | WorldClaw: Agentic 3D Open-World Generation at Scale | Chunchao Guo et al. | arXiv | 66 | |
| 2026-08-06 | 2608.05466 | Recursive Synthesis for Long-Horizon Terminal Tasks | Zhongzhi Li et al. | arXiv | 80 | |
| 2026-08-05 | 2608.02711 | Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing | Junliang Ye et al. | arXiv | 46 | |
| 2026-07-27 | 2607.22043 | Scaling Native Multimodal Pre-Training From Scratch | Haoyuan Wu et al. | arXiv | 28 | |
| 2026-07-22 | 2607.18722 | Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning | Junyao Yang et al. | arXiv | 33 | |
| 2026-07-17 | 2607.15273 | MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators | Yushi Huang et al. | arXiv | 12 | |
| 2026-07-16 | 2607.13285 | Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable | Ruhan Wang et al. | arXiv | 115 | |
| 2026-07-13 | 2607.08964 | Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading | Zongxia Li et al. | arXiv | 72 | |
| 2026-07-08 | 2607.02980 | Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling | Xiang Hu et al. | arXiv | 82 | |
| 2026-07-08 | 2607.05804 | TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training | Yuhang Zhou et al. | arXiv | 20 | |
| 2026-07-03 | 2607.02291 | Optimizing Visual Generative Models via Distribution-wise Rewards | Ruihang Li et al. | arXiv | 16 | |
| 2026-07-03 | 2606.27669 | When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search | Yiling Tao et al. | arXiv | 11 | |
| 2026-07-01 | 2606.32039 | GEAR: Guided End-to-End AutoRegression for Image Synthesis | Bin Lin et al. | arXiv | 15 | |
| 2026-07-01 | 2606.30673 | PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation | Chunshi Wang et al. | arXiv | 11 | |
| 2026-06-30 | 2606.29705 | GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots | Sunqi Fan et al. | arXiv | 14 | |
| 2026-06-26 | 2606.27313 | ViQ: Text-Aligned Visual Quantized Representations at Any Resolution | Xumin Yu et al. | arXiv | 28 | |
| 2026-06-24 | 2606.23543 | VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct | Haoling Li et al. | arXiv | 3 | |
| 2026-06-23 | 2606.23049 | Training Open Models for Agentic Phone Use | Zhengyang Tang et al. | arXiv | 18 | |
| 2026-06-23 | 2606.14971 | FastMix: Fast Data Mixture Optimization via Gradient Descent | Haoru Tan et al. | arXiv | 4 | |
| 2026-06-18 | 2606.19236 | STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability | Haipeng Luo et al. | arXiv | 5 | |
| 2026-06-15 | 2606.14409 | Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack | He Zhang et al. | arXiv | 15 | |
| 2026-06-08 | 2606.06891 | Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors | Hanxun Yu et al. | arXiv | 5 | |
| 2026-05-29 | 2605.30248 | GenClaw: Code-Driven Agentic Image Generation | Junyan Ye et al. | arXiv | 38 | |
| 2026-05-28 | 2605.28548 | GEM: Generative Supervision Helps Embodied Intelligence | Ruowen Zhao et al. | arXiv | 28 | |
| 2026-05-26 | 2605.26108 | Reinforcing Few-step Generators via Reward-Tilted Distribution Matching | Yushi Huang et al. | arXiv | 5 | |
| 2026-05-21 | 2605.20873 | PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models | Ziliang Zhao et al. | arXiv | 42 | |
| 2026-05-18 | 2605.11739 | Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation | Yuchen Cai et al. | arXiv | 15 | |
| 2026-05-18 | 2605.15876 | Unlocking Dense Metric Depth Estimation in VLMs | Hanxun Yu et al. | arXiv | 11 | |
| 2026-05-13 | 2605.11711 | Debiased Model-based Representations for Sample-efficient Continuous Control | Jiafei Lyu et al. | arXiv | 7 | |
| 2026-05-13 | 2605.04702 | FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation | Yuanzhi Wang et al. | arXiv | 1 | |
| 2026-05-13 | 2605.07545 | Implicit Preference Alignment for Human Image Animation | Yuanzhi Wang et al. | arXiv | 1 | |
| 2026-05-12 | 2605.09262 | Reinforcing Multimodal Reasoning Against Visual Degradation | Rui Liu et al. | arXiv | 5 | |
| 2026-05-12 | 2605.09269 | DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification | Rui Liu et al. | arXiv | 4 | |
| 2026-05-11 | 2605.06139 | Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex | Yun Qu et al. | arXiv | 73 | |
| 2026-05-07 | 2605.05185 | OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents | Shuang Chen et al. | arXiv | 53 | |