Daily AI Papers — August 13, 2026

1. Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

Authors: Zhuoyang Qian, Biao Wu, Yiran Wang, Chris D Yan, Desan Dai, Liangwei Zheng, Jin Jiang, Junsheng Zhang, Wenhao Wang arXiv: arxiv.org/abs/2608.11924 Summary: Turning a research idea into a complete paper requires more than text generation: the system must retrieve literature, design and execute experiments, revise claims according to evidence, produce publication-ready figures, and maintain consistency across a long generation process. We present Spark-to-Paper, an end-to-end research paper generation system implemented as thirteen composable skills inside an existing coding assistant, without requiring a separate agent platform or orchestration service. Trending because: 175 HuggingFace upvotes + one of the most-upvoted papers in today’s feed.

2. OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Authors: Yunhao Chen, Xin Wang, Yixu Wang, Yi Liu, Jie Li, Yan Teng, Xingjun Ma, Xia Hu, Yu-Gang Jiang arXiv: arxiv.org/abs/2608.00677 Summary: AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior is mediated through a shared state that is repeatedly modified and reused across long-horizon workflows. Trending because: 159 HuggingFace upvotes + one of the most-upvoted papers in today’s feed.

3. AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

Authors: Cheng Qian, Wenting Zhao, Liangwei Yang, Heng Wang, Jielin Qiu, Heng Ji, Silvio Savarese, Huan Wang, Shelby Heinecke arXiv: arxiv.org/abs/2608.12307 Summary: Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter’s parameters, through teacher forcing, on-policy distillation, and related training-time methods. In this paper, we ask whether such transfer can instead occur at test time. Trending because: 80 HuggingFace upvotes + strong engagement in today’s HuggingFace feed.

4. Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

Authors: Mengru Wang, Junfeng Fang, Shuofei Qiao, Zhenqian Xu, Haoming Xu, Haoxiong Wang, Shumin Deng, Linyi Yang, Zhixiang Cui, Xin Xu, Yunzhi Yao, Buqiang Xu, Fei Shen, Haozhe Luo, Yunxiang Wei, Ningyu Zhang, Julian McAuley, Tat Seng Chua, Huajun Chen arXiv: arxiv.org/abs/2608.12036 Summary: AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood. As AI development becomes faster and increasingly automated, mechanistic exploration remains largely manual, widening the gap between what models can do and our ability to understand and control them. Trending because: 72 HuggingFace upvotes + strong engagement in today’s HuggingFace feed.

5. SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

Authors: Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Liming Zhu, Wenjie Zhang arXiv: arxiv.org/abs/2608.05604 Summary: Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packages and loaded at inference time. As skill libraries grow, a central challenge is to expose the smallest sufficient executable context under a limited context budget. Trending because: 72 HuggingFace upvotes + strong engagement in today’s HuggingFace feed.

6. Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives

Authors: Yingpeng Ma, Jianhao Yan, Bei Shi, Ka Hou Kam, Runnan Wang, Xuebo Liu, Yulong Chen, Yue Zhang, Derek F. Wong arXiv: arxiv.org/abs/2608.08160 Summary: The rapid advancement of Large Language Models (LLMs) is revolutionizing AI for Games by enabling open-ended and fluid interactive storytelling. However, existing research has largely overlooked the critical challenge of maintaining long-horizon logical consistency and narrative integrity against unconstrained user interventions. Trending because: 25 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

7. StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization

Authors: Yuyang Yin, Zixiang Li, Longxuan Deng, Hongkai Li, Shifang Zhao, Junnan Liu, Weirong Huang, Mengyu Wang, Tianxiao Fu, Yikai Wang, Peng-Shuai Wang, Xiaojie Jin, Yao Zhao, Yunchao Wei arXiv: arxiv.org/abs/2608.12314 Summary: Previsualization is an intermediate layer between ideas and production in film, games, architecture, and urban design. It lets creators iteratively refine scenes, actions, cameras, and spatial-temporal dynamics. Trending because: 23 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

8. Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models

Authors: Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae, Jihyong Oh arXiv: arxiv.org/abs/2608.10708 Summary: Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization, achieving strong generalization. However, enforcing explicit multi-view geometric consistency, e.g., through bundle adjustment, is computationally costly and is thus not imposed during VFM pretraining, so such inconsistency can arise. Trending because: 12 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

9. SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

Authors: Xiaofan Bai, Hongqiang Lin, Chao Liu, Yantao Zhang, Xuan Jin, Xipeng Cao, Yuhong Li arXiv: arxiv.org/abs/2608.11079 Summary: Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several branches, examples, and warnings, while common action sequences are copied rather than reused. Trending because: 12 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

10. UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models

Authors: Lei Xin, Bin Gu, Peize Li, Zitong Wang, Jianbo Zhao, Changjiang Jiang, Yanyue Xie, Chao Huang, Xuyang Zhao, Zunhai Su, Fanhu Zeng, Zhenglun Kong arXiv: arxiv.org/abs/2608.08627 Summary: Sparse mixture-of-experts (MoE) layers expand recommendation capacity through conditional computation, yet a trained checkpoint still stores and routes over its full expert bank. We study a deployment problem: convert that checkpoint to a smaller standard MoE under an explicit expert budget, without adding a compression-specific online module. Trending because: 12 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

11. Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

Authors: Chris Han, Pengzhi Gao, Pei Fu, Jian Luan arXiv: arxiv.org/abs/2608.10812 Summary: We study reference-free post-training for multilingual machine translation with open large language models. Starting from the supervised-finetuned MiLMMT-46-v0.1 models, we apply Group Relative Policy Optimization (GRPO) with a reward that averages two reference-free quality estimation models and is gated by language identification. Trending because: 11 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

12. Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents

Authors: Harshitha Kolukuluru, Reshma Ashok, Kirat Arora, Evan William Ciccarelli, Nischal Ashok Kumar, Lunyiu Nie, Franck Dernoncourt, Samyadeep Basu, Ryan A. Rossi, Nedim Lipka arXiv: arxiv.org/abs/2608.08389 Summary: Long-horizon research agents solve open-ended tasks through iterative retrieval, aggregation, and synthesis, but context grows rapidly while the marginal value of additional evidence often declines. This leads to unnecessary token cost, higher latency, and noisier inputs for final report generation. Trending because: 11 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

13. SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

Authors: Junjie Ye, Zhuohui Sheng, Shaofan Liu, Yulun Zhu, Wenjie Fu, Dingwei Zhu, Ming Zhang, Yujiong Shen, Weichao Wang, Xin Zhao, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang, Pluto Zhou arXiv: arxiv.org/abs/2608.10692 Summary: Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across multiple applications (apps) to complete user instructions. However, due to the lack of dedicated benchmarks, their capabilities remain poorly understood. Trending because: 10 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

14. DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

Authors: Zhuchenyang Liu, Ziyi Wang, Yao Zhang, Yu Xiao arXiv: arxiv.org/abs/2608.10636 Summary: Visual document retrieval (VDR) is dominated by multi-billion-parameter models that are slow to index at full corpus scale and expensive to serve. Prior compression routes either train a smaller multi-vector encoder from scratch or distil only the query side; neither yields a compact single-vector retriever end-to-end. Trending because: 10 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

15. 360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents

Authors: Kenta Watanabe, Atsuyuki Miyai, Mizuki Takenawa, Kiyoharu Aizawa, Toshihiko Yamasaki arXiv: arxiv.org/abs/2608.08814 Summary: We present 360CityArena, a benchmark for evaluating the urban exploration capabilities of embodied agents within a photorealistic environment constructed from 360-degree videos. Existing outdoor benchmarks either lack sufficient photorealism or complexity, resulting in a considerable gap from real-world urban environments. Trending because: 10 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

16. InSight-doc: Agentic Visual Perception for Long-Document Understanding

Authors: Kaican Li, Weiyan Xie, Lewei Yao, Jiannan Wu, Lanqing Hong, Yongxiang Huang, Nevin L. Zhang arXiv: arxiv.org/abs/2608.10628 Summary: Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we propose InSight-doc, an agentic visual perception framework that treats visual resolution as an adaptive reasoning-time resource. Trending because: 10 HuggingFace upvotes + solid engagement in today’s HuggingFace feed.

17. Self-Evolving Embodied Agents via Skill-Harness Evolution

Authors: Peidong Wang, Zhiming Ma, Ying Chang, Xufang Luo, Xiaocui Yang, Shi Feng, Yuqing Yang, Dongsheng Li arXiv: arxiv.org/abs/2608.11350 Summary: Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces, and execution harness surrounding the model. While supervised fine-tuning and reinforcement learning can adapt agents to new environments, they require additional data, rewards, and training runs; meanwhile, many train-free code-centric approaches rely on programmable robot APIs that may be unavailable in fixed-interface settings. Trending because: 9 HuggingFace upvotes + notable topical significance among today’s fresh candidates.

18. TSDS-Toolbox: A Toolbox for Measuring Time-Series Dataset Similarity

Authors: Yen-Ku Liu, Hongjie Chen, Ryan A. Rossi, Franck Dernoncourt arXiv: arxiv.org/abs/2608.08119 Summary: The rapid advancement of artificial intelligence (AI) has significantly accelerated research in time-series analysis, particularly in forecasting, classification, and generation tasks. Recent models, especially foundation models, benefit from time-series dataset similarity due to its significant role in source dataset selection for fine-tuning. Trending because: 8 HuggingFace upvotes + notable topical significance among today’s fresh candidates.

19. iFAN: Inference-Aware Learning for Plain Mask Transformers

Authors: Fang Li, Yu He, Haoyang Tong, Lichen Ma, Jingling Fu, Wenxiao Fan, Tongxuan Liu, Luohang Liu, Ke Zhang, Junshi Huang arXiv: arxiv.org/abs/2608.03216 Summary: Query-based mask transformers assemble segmentation outputs through pixel-wise competition among query predictions of the final layer, yet this inference process is not explicitly optimized during training. We identify two key mismatches: the query with the highest probability-mask score does not necessarily produce the most accurate mask, and final-layer decoding may discard superior predictions from intermediate layers. Trending because: 8 HuggingFace upvotes + notable topical significance among today’s fresh candidates.

20. DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?

Authors: Mizanur Rahman, Mohammed Saidul Islam, Ridwan Mahbub, Md Tahmid Rahman Laskar, Shafiq Joty, Enamul Hoque Prince arXiv: arxiv.org/abs/2608.10366 Summary: Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of tools such as notebooks, IDEs, terminals, browsers, and databases within real operating environments. Yet existing benchmarks lack real-computer interaction and do not evaluate whether agents can execute complete end-to-end data-science workflows in realistic computing environments, failing to capture the multi-stage, multi-tool nature of data-science practice. Trending because: 7 HuggingFace upvotes + notable topical significance among today’s fresh candidates.