Daily AI Papers — August 25, 2026

1. Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Authors: Apodex Team, B. An, B. Li, B. Wang, B. Zhang, B. L. Wang, C. Feng, C. Wei, C. Xue, C. Zhang, D. Ng, D. Ye, E. Min, F. Chen, F. Liu, F. Yang, F. Ye, H. Xu, H. Yang, H. Ye, H. Zhang, H. Zhao, J. Li, J. Lin, J. Xia, K. Jin, K. Wang, K. Yang, L. Bing, L. Lei, L. Su, Le. Wang, Lu. Wang, N. Wang, Q. Ren, Q. Yang, R. Li, S. Bai, S. Du, S. Li, S. Lin, S. Nie, S. Wang, S. Zhang, S. Z. Wang, Ta. Q. Fang, Ti. Q. Fang, W. Fang, W. Li, W. Zhang, X. Chen, X. Li, X. Tang, X. Wang, X. Xu, X. Zhang, X. Q. Wang, X. Y. Wang, Y. Deng, Y. Gao, Y. Hu, Y. Li, Y. Sui, Y. Wang, Y. Xiao, Y. Zhang, Z. Chen, Z. Cheng, Z. Feng, Z. Liang, Z. Zhang arXiv: arxiv.org/abs/2608.23283 Summary: General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state maintenance, failure recovery, and verifiable delivery. We call this working capability: sustained, verifiable progress toward a real-world objective. Trending because: 165 HuggingFace upvotes + timely work on autonomous agents

2. EchoWM: Open and Enterable Omnimodal World Models

Authors: Songchun Zhang, Yaowei Li, Junhao Zhuang, Weiyang Jin, Haoyu Wang, Xin Lu, Yilang Sun, Shiyi Zhang, Haoran Li, Xiaoxiao Ma, Yuming Li, Yijun Liu, Yaofeng Su, Yanwen Ma, Haoyu Wu, Zihan Su, Yue Ma, Lvmin Zhang, Haoyang Huang, Zeyue Xue, Anyi Rao, Nan Duan arXiv: arxiv.org/abs/2608.23189 Summary: We present EchoWM, an omnimodal world model for enterable generative media that responds to continuous navigation while jointly generating 720p video, environmental sound, music and speech. We organize interaction around camera intent: in first-person scenes, it specifies observer motion, while in third-person scenes, camera–character dynamics are learned from data without view-specific controllers. Trending because: 62 HuggingFace upvotes + growing momentum around world models

3. TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

Authors: Yibo Hu, Yu Qian, Mao Gu, Yingfan Tao, Yuhao Chen, Yongdong Luo, Zhuoqun Liu, Meiguang Jin, Junfeng Ma arXiv: arxiv.org/abs/2608.20958 Summary: E-commerce live streaming requires omni-modal understanding of noisy, temporally extended streams, where product facts are distributed across speech, video frames, product images, overlaid text, and user queries. We present TLive-Omni, an omni-modal understanding model tailored to live-commerce scenarios. Trending because: 51 HuggingFace upvotes + a widely-watched new benchmark

4. Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision

Authors: Long Cui, Xiaoqian Liu, Qi Qin, Yi Xin, Tao Lin, Jianguo Li, Linfeng Zhang arXiv: arxiv.org/abs/2608.16812 Summary: Existing image editing frameworks predominantly follow the training paradigm of text-to-image diffusion models. However, extending this paradigm to image editing highlights two inherent discrepancies, specifically, the insufficient attention to edit concept granularity and the training inefficiency caused by sparse supervision signals. Trending because: 45 HuggingFace upvotes + an eye-catching result in generative editing

5. MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks

Authors: Yi Zhu, Xiongwei Wu, Qiyi Wang, Tingyu Qu, Jiajun Liu, Sihan Cao, Long Chen, Weigao Sun, Feida Zhu, Yiran Zhong, Steven Hoi arXiv: arxiv.org/abs/2608.23035 Summary: As on-device LLM agents evolve into personal copilots, the mobile operating system has become a key testbed for this paradigm, making rigorous capability evaluation essential. Yet existing benchmarks fall into two camps, each with a critical blind spot: GUI-centric benchmarks test surface-level screen manipulation while overlooking background tool use and long-horizon planning, whereas static function-calling benchmarks rely on offline API matching that is detached from real runtime constraints. Trending because: 33 HuggingFace upvotes + timely work on autonomous agents

6. Prime Agent: A Self-Improving RLM Harness

Authors: Seth Karten, Alex L. Zhang, Kevin Thomas, Sebastian Müller, Elie Bakouch, Daniel Auras, Mika Senghaas, Fares Obeid, Konstantin Dunas, Johannes Hagemann, Sami Jaghouar arXiv: arxiv.org/abs/2608.23552 Summary: Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent workflows. Trending because: 31 HuggingFace upvotes + timely work on autonomous agents

7. Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Authors: Bowen Cui, Weijie Wang, Zeyu Zhang, Yefei He, Mingda Lin, Haoyu Zhao, Yuanyu He, Donny Y. Chen, Feng Chen, Bohan Zhuang arXiv: arxiv.org/abs/2608.19567 Summary: While text-to-3D generation has advanced rapidly, achieving high geometric fidelity at low inference cost remains challenging. Existing text-to-3D methods either decode discrete shape tokens autoregressively or iteratively refine global 3D representations with diffusion or flow models. Trending because: 25 HuggingFace upvotes + fast-moving 3D generation research

8. RISE: Adaptive Imagination for World Action Models

Authors: Hongbo Lu, Liang Yao, Chenghao He, Hao Han, Fan Liu, Wenlong Liao, Tao He, Pai Peng arXiv: arxiv.org/abs/2608.20430 Summary: World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagination budget to every scene. We propose RISE (Refining Imagination through SElective Rollout), a system-level adaptive imagination framework that makes sequential Roll/Stop decisions according to the expected planning benefit of continued rollout. Trending because: 24 HuggingFace upvotes + growing momentum around world models

9. Towards a Densing Law for User Representation Learning at Billion-Scale Capacity

Authors: Bin Dou, Junru Zhang, Zhaoyi Yuan, Wuliang Huang, Letian Gong, Baokun Wang, Huan Li, Yu Cheng, Weiqiang Wang arXiv: arxiv.org/abs/2608.23392 Summary: User representation learning in real-world industrial scenarios is commonly scaled by increasing user amount, behavioral sequence length and model size. However, existing methods face two challenges: (i) Bottleneck for raw data scaling at billion-scale capacity, as performance exhibit diminishing performance gains with larger-scale raw text user behavioral input, which can be mitigated by tokenization. Trending because: 20 HuggingFace upvotes + scaling laws for representation learning

10. ReWorld: An Interactive World Model with Long-Horizon Memory

Authors: Zhifei Chen, Luozhou Wang, Guibao Shen, Dongyu Yan, Shuai Yang, Tianshuo Xu, Yihua Du, Wei Wang, Tianyi Gui, Lianghua Huang, Yingcong Chen arXiv: arxiv.org/abs/2608.23565 Summary: An interactive world model must follow the user’s actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounded one. Trending because: 14 HuggingFace upvotes + growing momentum around world models

11. ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction

Authors: Yongqi Tong, Tan Li Hui Faith, Choy Zhen Wen Marcus, Zhou Jin, Kewei Fu, Jiang-Ming Yang, Jianshe Li, Xin Zhang arXiv: arxiv.org/abs/2608.13622 Summary: Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarification, provide progress updates, or confirm before acting. This flexibility breaks a core assumption behind group-based RL: rollouts compared within a group are no longer guaranteed to be behaviorally comparable. Trending because: 14 HuggingFace upvotes + timely work on autonomous agents

12. Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization

Authors: Xianlei Zhou, Xiangdi Meng, Yu He, Tianyu Qi, Shuyan Guan, Xianli Zhang, Jian Zhang, Xin Li, Qika Lin, Jun Liu arXiv: arxiv.org/abs/2608.23311 Summary: Policy optimization (PO) for Large Language Models faces a stability–exploration trade-off, currently mediated by an action-side Policy-KL regularizer. This puts practitioners in a double bind: keeping Policy-KL constrains response behavior and consumes the action-side exploration budget, while dropping it leaves the optimization without an explicit drift control. Trending because: 13 HuggingFace upvotes + a widely-watched new benchmark

13. WorldMind: Decoupled Game World Model for State-Aware NPC Behavior

Authors: Zhiyang Deng, Boran Zhang, Danze Chen, Yeying Jin arXiv: arxiv.org/abs/2608.21439 Summary: Game world models have recently demonstrated promising capabilities in generating visually coherent and action-controllable gameplay videos. However, non-player character (NPC) behavior in existing models is either implicitly entangled with video generation or explicitly prescribed through external control signals. Trending because: 13 HuggingFace upvotes + timely work on autonomous agents

14. GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?

Authors: Kun Chen, Haorong Hong, Peizhong Gao, Jianfeng Lin, Tongxu Luo, Yuxuan Xie, Chenxu Liu, Jieling He, Zhongyuan Liu, Zeno Zeng arXiv: arxiv.org/abs/2608.21833 Summary: Recent large language models (LLMs) can operate as coding agents that build complete games from natural language requests. Game development is especially demanding because program logic, visual and audio content, interfaces, interaction and playability must function together in one executable artifact. Trending because: 11 HuggingFace upvotes + timely work on autonomous agents

15. Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

Authors: Bakbergen Ryskulov, Iker García-Ferrero, David Montero, David Jansen, Ali Hashemi, Jezabel R. Garcia, Antonio Tiene, Román Orús arXiv: arxiv.org/abs/2608.20953 Summary: Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and quantized to 4 bits. Together these steps degrade reasoning, mathematics, coding, and long-context behavior enough to require a recovery, or healing, stage before deployment. Trending because: 8 HuggingFace upvotes + a widely-watched new benchmark

16. One Success Isn’t Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows

Authors: Zhuochun Li, Youngmin Ko, Ali Keramati, Nicola Ferri, Susana Palmaz Lopez Pelaez, Liang-Chun Tsai, Calvin Wang, Mirco Milletari, Tuhin Kundu, Vadim Smolyakov, Kjartan Olafsson, Tommy Guy arXiv: arxiv.org/abs/2608.19741 Summary: Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Yet completing consequential work beyond code requires more than producing a plausible response or valid tool call: agents must gather missing information over multiple turns, follow domain policies, coordinate dependent tools, and realize the correct persistent state transition without collateral effects. Trending because: 8 HuggingFace upvotes + timely work on autonomous agents

17. Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress

Authors: Chen Yang, Haiyuan Wan, Rengrong Xiong, Yize Chen, Danny H. K. Tsang arXiv: arxiv.org/abs/2608.19408 Summary: On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing student-generated trajectories with dense token-level supervision from a teacher. However, OPD implicitly assumes that teacher-derived rewards are an appropriate proxy for reasoning progress, and therefore treats all teacher feedback equally during policy optimization. Trending because: 7 HuggingFace upvotes + practical advances in model distillation

18. Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection

Authors: Atsuyuki Miyai, Kiyoharu Aizawa, Toshihiko Yamasaki arXiv: arxiv.org/abs/2608.20169 Summary: We present a novel approach to efficient LLM harness optimization through adaptive validation task selection. Harness optimization iteratively rewrites the harness code based on validation performance, enabling substantial performance gains without updating the underlying model weights. Trending because: 6 HuggingFace upvotes + timely work on autonomous agents

19. AutoResearch: Insight In, Hallucination Out

Authors: Yiming Ren, Xiang Liu, Qumeng Sun, Xiao Zhang, Jiahao Li, Haoyang Zhang, Junjie Wang arXiv: arxiv.org/abs/2608.17906 Summary: Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We introduce AutoResearch, a two-stage system that connects Idea Generation with Idea Execution to address both how research ideas are formed and how they are reliably established through experimentation. Trending because: 6 HuggingFace upvotes + timely work on autonomous agents

20. Hydra-0: Action Flow for Generalist World Modeling and Control

Authors: Hongyu Li, Bowen Wen, Xinghao Zhu, Yixuan Wang, Yilun Du, Yunzhu Li, George Konidaris, Stan Birchfield, Soha Pouya, Chenran Li, Yan Chang arXiv: arxiv.org/abs/2608.18077 Summary: We introduce Hydra-0, a generalist world model conditioned on action flow, which represents robot actions as pixel motion. This shared visual interface enables generalist world modeling and control by learning action consequences across embodiments, tasks, environments, and video-generation backbones. Trending because: 6 HuggingFace upvotes + growing momentum around world models