Hugging Face daily papers, ranked by community upvotes. Summaries and key terms are written by Workers AI from the abstract — click a term to filter, or search below (matches full abstracts and authors too).
667 upvotes · 15 OCT 2026 · Bingxi Hou, Guochao Jiang, Guofeng Quan et al.
This paper develops a method to transfer policy shifts from a reinforcement learning (RL) teacher to a student model, using an intermediate teacher checkpoint to compare early and late policy shifts and gate the endpoint shift based on their agreement. Practitioners in RL and reinforcement learning may care about this paper because it proposes a more effective way to transfer policy shifts, which is crucial for improving student performance in various domains.
548 upvotes · 10 AUG 2026 · Björn Engdahl, Adrian Kosowski, Jan Chorowski et al.
This paper introduces a new AI model called BDH-CQ that can learn from context and reason iteratively without verbalizing its steps. Practitioners might care because this model achieves a high level of performance while being very efficient, which could be useful for applications where resources are limited.
454 upvotes · 10 SEP 2026 · Jintao Zhang, Kai Jiang, Jintao Chen et al.
This paper introduces Vidu S2, a system that can generate and edit video in real-time, allowing for interactive and editable video content. Practitioners might care because this technology could enable new forms of video creation and editing.
452 upvotes · 29 AUG 2026 · Xiyuan Yang, Sheikh Sarwar, Jingru Cheng et al.
This paper proposes a method to scale automatic research agents by replacing environment execution with a world model, which can reduce training costs and improve performance. Practitioners might care about this approach because it can accelerate training times and lead to better results for complex AI tasks.
424 upvotes · 14 SEP 2026 · Honglin Guo, Tao Gui, Yicheng Chen et al.
This paper introduces Atria Dawn Preview, a new type of AI model designed to work alongside humans in scientific research and engineering. Practitioners might care about this because it shows how AI can collaborate with humans more effectively, potentially leading to better research outcomes and more autonomous AI development.
399 upvotes · 1 SEP 2026 · Ke Yang, Chenglong Wang, Michel Galley et al.
This paper develops a method to create personalized AI tutors that can adapt to individual students' strengths and weaknesses, using a combination of pooled training and per-student fine-tuning. Practitioners in education and AI development may care about this work as it could lead to more effective and personalized learning experiences.
387 upvotes · 2 SEP 2026 · Jianlyu Chen, Yuyang Hu, Hongjin Qian et al.
This paper creates a system that extracts and distills AI skills from GitHub repositories to help autonomous agents learn and perform machine learning tasks more efficiently. Practitioners might care because it could improve the performance of AI research agents in real-world applications.
385 upvotes · 26 OCT 2026 · Weidong Tang, Ruiheng Wang, Jingxuan Zhang et al.
This paper proposes a framework called The Trinity to improve multimodal agents by recursively self-improving their capabilities. Practitioners may care because it can lead to significant performance gains in various tasks, including real-world embodied ones.
379 upvotes · 26 OCT 2026 · Tao Ren, Hui Yang, Jia Deng et al.
This paper proposes a new optimization technique for long-horizon language model agents, allowing them to make more informed decisions by allocating credit more finely across individual tokens. Practitioners might care because it could lead to better performance in tasks like search, tool-use, and automation.
377 upvotes · 3 SEP 2026 · Yuntian Deng, Pengyu Nie, Stuart Shieber
This paper introduces a method to compile neural functions from natural-language specifications, allowing for faster and more reliable execution without relying on remote models. Practitioners may care about this approach for building efficient and flexible AI systems that can perform complex tasks without the need for expensive model calls.
371 upvotes · 15 SEP 2026 · Xingxuan Zhang, Gang Ren, Hao Yuan et al.
This paper introduces LimiX-2, a new AI model that uses a new paradigm called Contextual Mechanism Networks (CMNs) to learn from structured data. Practitioners might care about this because it could lead to more accurate and causal AI models.
360 upvotes · 31 AUG 2026 · Xin Zhou, Zongchuang Zhao, Zhibo Yang et al.
This paper develops a vision-language model for autonomous driving that combines 3D perception, question answering, and motion planning. A practitioner might care because it demonstrates a promising approach to integrating multiple tasks in autonomous driving.
353 upvotes · 15 OCT 2026 · Luozheng Qin, Yuhan Zhu, Changhai Zhou et al.
This paper introduces MJev-Spatial, a new AI model that can quickly understand and act in the physical world by using a unified classification framework to answer spatial intelligence tasks. Practitioners may care about this model because it can solve real-world problems faster and more efficiently than existing models.
340 upvotes · 25 OCT 2026 · Yihao Hu, Yitong Lin, Pan Wang et al.
This paper addresses a problem in training spatial vision-language models (VLMs) where the model becomes specialized in answering certain types of questions, but loses its ability to perform well on others. A new method called ChronoReplay is proposed to improve the model's ability to generalize across different question types.
338 upvotes · 27 JUL 2026 · Kimi Team, Tongtong Bai, Yifan Bai et al.
This paper introduces Kimi K3, a large-scale, open-source AI model that achieves state-of-the-art performance on a range of tasks, including vision and coding, and is designed to be more efficient and scalable than previous models, making it a promising candidate for real-world applications.
331 upvotes · 8 SEP 2026 · NeoHorse Team, Guoliang Cao, Guohao Dai et al.
This paper proposes a method for recursive self-improvement in AI systems, where a model can learn from its own performance and use that knowledge to improve itself. Practitioners might care about this approach because it could lead to more efficient and effective AI systems.
330 upvotes · 24 OCT 2026 · Yihao Hu, Zhihao Wen, Yitong Lin et al.
This paper creates a new way to teach AI agents to use tools by generating realistic interactions that show how to use tools in a step-by-step way. Practitioners might care because it helps agents learn to use tools more effectively, especially in situations where the agent needs to remember previous actions and decisions.
316 upvotes · 15 OCT 2026 · Hanzhang Zhou, Long Li, Quyu Kong et al.
This paper develops OpenGCUA, an open-source platform for generalist computer-use agents that can interact with users through both visual and programmatic interfaces. Practitioners might care about OpenGCUA because it could lead to more efficient and flexible AI systems that can handle a wide range of tasks.
311 upvotes · 15 AUG 2026 · Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang et al.
This paper introduces StateM, a runtime system that improves the performance of long-horizon agents by organizing their execution around durable states, phase-local context, and other components. Practitioners might care because StateM can help agents achieve higher accuracy and efficiency, especially in complex tasks.
304 upvotes · 9 SEP 2026 · NCP Team, Jiaqi Cao, Chiyu Chen et al.
This paper introduces a new type of language model called NCP-ArchPreview that can generate text by predicting both individual tokens and larger concepts, and how this approach can improve performance. Practitioners might care about this because it could lead to better language models that can handle more complex tasks.
302 upvotes · 11 SEP 2026 · Jiyan He, Guang Liang, Hao Liu et al.
This paper introduces ZGCM-1, a highly efficient foundation model for math and agentic search that combines internal thinking with external tool use, and shows it can perform well on various benchmarks despite its compact size. Practitioners may care about the efficiency improvements and scalable architecture of ZGCM-1.
294 upvotes · 7 SEP 2026 · Zheyuan Zhang, Alvin Zhang, Daniel Khashabi et al.
This paper explores a way for language models to remember information from previous updates, even after many changes, and finds that combining different techniques can lead to much better retention than using any one technique alone.
292 upvotes · 30 JUL 2026 · Hanzhang Zhou, Panrong Tong, Xu Zhang et al.
This paper introduces Qwen-UI-Agent, a type of artificial intelligence system that can perform tasks on various devices, such as smartphones and computers, and improve its abilities on its own. Practitioners might care about this research because it aims to create more practical and autonomous AI systems that can be used in real-world scenarios.
292 upvotes · 30 JUL 2026 · Bing Yan, Gregory Wolfe, Stefano Martiniani et al.
This paper creates a system to help scientists and AI agents find and verify specific information in chemistry literature by converting research papers into claims, which are then linked together to form a network of evidence. Practitioners might care because this system could improve the efficiency and accuracy of literature synthesis in chemistry research.
292 upvotes · 20 OCT 2026 · StreamEval Team
This paper introduces a benchmark, StreamEval, to evaluate interactive streaming video generation models, which is essential for enabling real-time interaction with generated video in applications like streaming services. Practitioners caring about the development of interactive video generation systems will find this paper useful.
285 upvotes · 15 OCT 2026 · Dongxu Yang, Hongda Yan, Renxin Wang et al.
This paper creates a benchmark for evaluating AI systems in real-world customer delivery scenarios, where agents must clarify ambiguous requirements, work in live systems, and uncover unstated constraints. Practitioners might care because it highlights the challenges of delivering effective AI systems in complex, real-world environments.
272 upvotes · 3 SEP 2026 · Jie Wu, Zhenru Zhang, Beichen Zhang et al.
This paper develops a method to turn agent trajectories into reusable environments, allowing for more efficient testing and interaction with the agent. Practitioners might care because this approach can help scale agent training and improve performance in various applications.
271 upvotes · 9 OCT 2026 · Zhiyuan Shi, Xiang Li, Xingzhuo Guo et al.
This paper discovers an internal spatial representation space in multimodal language models that allows them to reason about spatial relationships and locations, and how this space is used to support accurate spatial judgments. Practitioners might care because it helps them understand the limitations of large-scale language models in spatial reasoning tasks.
258 upvotes · 20 AUG 2026 · Chengsong Huang, Zifeng Wang, Rujun Han et al.
This paper introduces EnvHarness, a tool that lets AI agents learn from static environments by changing how they interact with those environments, without having to rebuild the environments from scratch. This can help improve the performance of AI agents in real-world applications.
257 upvotes · 14 AUG 2026 · Shuo Liang, Yixing Ma, Pengfei Zhou et al.
This paper evaluates the effectiveness of video detectors against AI-generated video attacks on real-world crisis events and finds that current methods struggle to detect realistic fake videos, highlighting the need for improved detectors. Practitioners might care about developing more robust video detectors to prevent the spread of misinformation.
256 upvotes · 29 JUL 2026 · Zeyu Zhang, Ziliang Guo, Yihang Sun et al.
This paper introduces a new type of AI model called memory foundation models, which allows the model to learn and retain information internally, rather than relying on external memory modules. This could be useful for practitioners who want to build more efficient and flexible AI agents.
256 upvotes · 14 SEP 2026 · Tong Zheng, Xidong Wu, Zheng Zhang et al.
This paper introduces Dream-RSI, a framework for recursive self-improvement in exploration, which helps autonomous AI agents discover high-value solutions more efficiently by using a replay simulator to provide low-cost feedback. Practitioners might care because effective exploration is crucial for AI progress, and Dream-RSI can improve discovery quality and reduce costs.
252 upvotes · 1 AUG 2026 · Yunhao Chen, Xin Wang, Yixu Wang et al.
This paper introduces OpenART, a platform for testing AI agents in open-ended environments, to evaluate their safety in complex and evolving scenarios. Practitioners can use OpenART to identify potential risks and improve the robustness of their AI systems.
248 upvotes · 10 SEP 2026 · Haiwen Diao, Jiahao Wang, Chenjing Ding et al.
This paper introduces SenseNova-U1.5, a powerful AI model that can understand, reason about, and generate visual content without needing a separate text-to-image model. Practitioners might care because this model can be used to create complex visual content, such as images and videos, with high fidelity and accuracy.
242 upvotes · 22 OCT 2026 · Tianming Liang, Junyi Pan, Yuxi Li et al.
This paper develops a vision-language model (VLM) that can accurately perceive objects and pixels in images, which can be useful for various applications such as self-driving cars, medical imaging, and augmented reality. Practitioners in these fields may care about the potential improvements in visual perception and object detection that this model can bring.
238 upvotes · 24 SEP 2026 · Ziyang Zhang, Yubin Jing, Yuanhao Zeng et al.
This paper discovers that language models can learn from unrelated text after being trained on a specific task, and introduces a method called Active Taskless Distillation (ATD) that allows this capability transfer to happen without using target-task examples or teacher parameters. Practitioners might care because it could lead to more efficient and effective language model training.
238 upvotes · 30 SEP 2026 · Qize Yu, Lianrui Fan, Boyu Chen et al.
This paper introduces GroundingPI, a new AI model that improves its ability to understand and interact with the physical world by learning to precisely identify objects and their locations, even in cluttered environments. Practitioners may care about GroundingPI's potential to enhance applications like robotics, autonomous driving, and object recognition.
236 upvotes · 1 SEP 2026 · Yuhao Wu, Jingyuan Zhang, Jiajun Shi et al.
This paper creates a benchmark (HarnessDev) to test whether large language models (LLMs) can design and improve their own execution infrastructure, called the agent harness, which affects their performance. Practitioners might care because it explores how models can adapt to changing environments and potentially improve efficiency.
235 upvotes · 26 OCT 2026 · Chengzhi Liu, Yuxiang Lai, Yuzhe Yang et al.
This paper develops proactive video agents that can understand and respond to user intent in real-time, improving interaction quality and response timing. Practitioners can benefit from this research to create more intuitive and responsive video interfaces.
233 upvotes · 15 OCT 2026 · SenseNova, Joint Research Team, Zhongang Cai et al.
This paper evaluates GPT-6-Astra's robotic manipulation and navigation capabilities, demonstrating its ability to perform tasks that require physical interaction and adaptation. Practitioners in AI and robotics might care about this research as it challenges traditional approaches to building specialized models for individual tasks and could lead to more efficient and effective embodied intelligence.
230 upvotes · 19 OCT 2026 · Zhuofan Josh Ying, Guanglong Sun, Nolan Ho et al.
This paper develops a method to efficiently fine-tune large pretrained models for brain encoding, allowing for the adaptation of models with up to 104B parameters. Practitioners might care because this approach enables better performance and interpretability for brain encoding tasks.
227 upvotes · 3 SEP 2026 · Chuyan Chen, Haoxing Chen, Kun Chen et al.
This paper introduces a new framework for building strong image generators that can produce highly photorealistic images while accurately following editing instructions. Practitioners might care about the potential applications of this framework in fields like computer vision, graphics, and art.
226 upvotes · 8 OCT 2026 · Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang et al.
This paper introduces a new method for reinforcement learning with diffusion models, called DiffusionART, which combines the benefits of forward-process and reverse-process methods to improve efficiency and stability. Practitioners might care about this method because it can train diffusion models more effectively and efficiently than existing methods.
223 upvotes · 5 AUG 2026 · Zhongzhi Li, Yucheng Shi, Zongxia Li et al.
This paper introduces a method to generate long-horizon training tasks for terminal agents at scale, which can be used to improve AI models' performance on tasks like navigation and decision-making. Practitioners might care about this because it could help train more advanced AI models with better performance on complex tasks.
219 upvotes · 22 OCT 2026 · Shengqiong Wu, Meng Luo, Bobo Li et al.
This paper surveys the development of video world models that capture the underlying dynamics of the world depicted in videos, and how they relate to video foundation models. Practitioners in AI and machine learning might care about this research because it aims to create more realistic and interactive video models that can be used in applications such as virtual reality, robotics, and autonomous systems.
210 upvotes · 31 AUG 2026 · Yuhao Wu, Jingyuan Zhang, Jiajun Shi et al.
This paper introduces ASPIRE, a benchmark for self-evolving models that can learn from vague goals, and explores how agents can interpret and operationalize these goals to improve their performance. Practitioners may care about how models can learn from unclear objectives in real-world applications.
209 upvotes · 23 SEP 2026 · Haotian Zhang, Fengyuan Yu, Dezhi Luo et al.
This paper investigates whether video generation models, which are a type of world model, have a basic understanding of object permanence and can be improved through training. Practitioners interested in building human-like physical intelligence may care about this research as it could lead to more realistic and interactive AI systems.
208 upvotes · 8 OCT 2026 · Dianqiao Lei, Kevin Qinghong Lin, Pan Lu et al.
This paper investigates how Large Language Models (LLMs) behave when "told not to think", i.e., when instructed to produce answers without using reasoning. Practitioners might care about understanding how to control this behavior, as it can impact the accuracy of LLMs in certain tasks.
206 upvotes · 13 OCT 2026 · Qi Li, Xinchao Wang
This paper introduces Jeva, a decision-native architecture that improves the performance of system one models by addressing four structural requirements: distinguishing answer absence from uncertainty, being permutation-invariant, scaling with option sets, and allowing cacheable computation. Practitioners caring about decision-making in AI systems might care about Jeva's approach to handling decision problems.
205 upvotes · 12 SEP 2026 · Ruixiang Zhao, Hualei Wang, Renhe Sun et al.
This paper introduces Realtime-Venus, a full-duplex interaction system that combines audio-visual and spoken interaction capabilities to enable continuous and timely responses in digital and physical environments. Practitioners in the field of human-computer interaction may care about this research as it presents a proactive approach to interaction systems that can handle multiple input streams and respond accordingly.
202 upvotes · 14 OCT 2026 · Qingchuan Ma, Yuexiao Ma, Xiang Meng et al.
This paper evaluates how well vision-language models can understand 3D objects from 2D observations and make precise actions. Practitioners might care because it highlights the limitations of current models in tasks that require inferring object geometry and anticipating the effects of rotation.
201 upvotes · 9 OCT 2026 · Jiahao Wang, Hongjin Qian, Yuyang Hu et al.
This paper creates a benchmark to test how well coding agents can build agents that meet their users' needs, and it finds that most agents fail to deliver what they promise. Practitioners might care because it highlights the need for better evaluation methods to ensure agents are built to meet user requirements.
201 upvotes · 13 OCT 2026 · Chuyang Wei, Haoxiang Guan, Minghang Zhu et al.
This paper proposes a framework for self-evolving agents that can adapt to changing environments by modifying their software scaffolding without changing their model weights. This approach has implications for reliability, accountability, and knowledge sharing in various domains, including scientific research and organizational workflows.
199 upvotes · 21 JUL 2026 · Fan Jiang, Zhaoxu Sun, Mengchao Wang et al.
This paper presents a video world model that can interact with a virtual environment in real-time, using a single desktop GPU. Practitioners might care about the potential applications of this technology in areas like virtual reality, gaming, and robotics.
192 upvotes · 13 OCT 2026 · Guanting Dong, Xinyu Yang, Jiajie Jin et al.
This paper teaches language agents to reflect on their actions and adapt to changing environments, allowing them to learn from feedback and correct mistakes more effectively. Practitioners can benefit from this approach in real-world applications where agents need to handle noisy feedback and user corrections.
185 upvotes · 26 AUG 2026 · Pengfei Zhou, Hexin Wang, Zhengfeiyang Zhang et al.
This paper proposes a way to improve the efficiency of training world models by using game development as a source of reward signals and trajectory data, allowing for more effective post-training of large language models using reinforcement learning. Practitioners might care about this approach because it could lead to more scalable and effective world models for applications like dialogue systems and visual question answering.
184 upvotes · 17 OCT 2026 · Wen Xue, Yong Liu, Xueheng Li et al.
This paper introduces a new framework called LayerEditor that allows for precise image editing by generating reusable RGBA layers, enabling users to control individual layer content and manipulate the image in a more flexible way. Practitioners might care about this development if they need to create high-quality images with precise local manipulation and layer reuse.
183 upvotes · 9 AUG 2026 · Yijiang Li, Bingyang Wang, Yijun Liang et al.
This paper shows how to make large language models improve themselves without needing external guidance or supervision, by using their own internal consistency to correct mistakes. Practitioners might care about this because it could lead to more robust and self-sufficient AI models.
182 upvotes · 25 OCT 2026 · Ruhao Liu, Qi Li, Shizun Wang et al.
This paper introduces DynaFlow, a framework that enables multi-agent systems to adapt to diverse task requirements by learning to orchestrate sub-agents in a free-form way. Practitioners might care about DynaFlow because it can improve the flexibility and performance of multi-agent systems in real-world applications.
180 upvotes · 11 AUG 2026 · Qianggang Ding, Xingyao Wang, Rui Feng et al.
This paper introduces Combodied Agents, a new approach to Agentic AI that focuses on understanding and supporting individual human-state trajectories over time, rather than just completing tasks. Practitioners might care about this because it has the potential to improve human-AI interactions and provide more effective support for people's needs.
179 upvotes · 30 SEP 2026 · Fang Wu, Da Xing, Yanjie Huang et al.
This paper introduces UniEvo-VL, a self-improvement framework for multimodal models that uses their own feedback to learn and improve, without relying on an external teacher. Practitioners might care because it can lead to better image generation capabilities and more efficient models.
176 upvotes · 12 AUG 2026 · Zhuoyang Qian, Biao Wu, Yiran Wang et al.
This paper presents a system that can generate research papers end-to-end, from retrieving literature to producing publication-ready figures, and includes checks to ensure the accuracy and validity of the research. Practitioners might care about this system because it could streamline the process of writing research papers and reduce errors.
176 upvotes · 20 OCT 2026 · Jihai Zhang, Runjia Qian, Kaiqin Kong et al.
This paper creates a new system that allows for real-time, playable game worlds using video models, enabling players to interact with and modify the game environment in a more immersive way. Practitioners might care about this technology for creating new types of interactive experiences.
173 upvotes · 22 OCT 2026 · Songlin Yang, Zhe Wang, Xiaotong Zhao et al.
This paper proposes a method to use multimodal large language models (MLLMs) to improve cinematic video generation by providing both temporal inference and factor-aware control. A practitioner might care about this paper if they want to generate more realistic and controllable videos.
172 upvotes · 14 SEP 2026 · DeepCybo Team, Yu Bin, Haipeng Cao et al.
This paper develops a unified model that can understand physical environments, generate actions, and predict future states, using a combination of vision, language, and embodied interactions. Practitioners may care about this model because it could be used to create robots or other agents that can interact with and adapt to their physical surroundings.
171 upvotes · 11 AUG 2026 · Zihao Liu, Xiaolong Shen, Zhenglin Zhou et al.
This paper develops a method to generate 4D worlds from text or images by leveraging the latent space of a video prior. It allows for more flexible and reusable 4D prediction, enabling practitioners to create more realistic and stable 3D scenes.
171 upvotes · 26 AUG 2026 · Xuan He, Cong Wei, Yuhao Cheng et al.
This paper introduces VGI-bench, a new benchmark for evaluating video generation models' visual reasoning capabilities, and finds that current models can solve some visually grounded tasks but still struggle with reliability. Practitioners may care about developing more reliable video generation models that can perform better on this benchmark.
169 upvotes · 24 AUG 2026 · Apodex Team, B. An, B. Li et al.
This paper develops a new AI system called Apodex that can perform sustained, verifiable progress on complex tasks, such as professional work, research, and coding, by combining reasoning, state maintenance, and interaction with files and code. A practitioner might care about Apodex because it can potentially automate complex tasks more effectively than current AI systems.
168 upvotes · 30 JUL 2026 · Junlin Yang, Che Jiang, Yu Fu et al.
This paper trains an AI model to improve itself in the process of building AI, with a focus on machine learning engineering, and shows promising results in various benchmarks. Practitioners may care about this research as it could lead to more efficient and autonomous AI development.
168 upvotes · 26 AUG 2026 · Zhifei Xie, Jiaqi Lang, Ze An et al.
This paper introduces VoiceMem, a memory system for conversational AI that combines accuracy, emotional awareness, and real-time performance. Practitioners might care because it provides a foundation for building more human-like speech interaction systems.
168 upvotes · 28 SEP 2026 · Julianna Piskorz, Antonin Berthon, Mihaela van der Schaar
This paper compares the effectiveness of on-policy and off-policy learning in a distillation setting, finding that rollout policy is not as crucial as previously thought, and that learning rate and token-level KL direction play more significant roles in task performance and forgetting.
167 upvotes · 30 SEP 2026 · Meijia Chen, Hao Li, Zheng Lu et al.
This paper identifies a problem in self-evolving search agents where the proposer and solver agree on errors, leading to improved internal reward without better external performance. Practitioners might care about this issue to develop more reliable search agents that can learn from their mistakes.
166 upvotes · 3 SEP 2026 · Heng Wang, Jielin Qiu, Wenting Zhao et al.
This paper proposes a new method for managing the memory of large language models, called Random Attention, which improves their performance on tasks that require extended reasoning by reducing memory usage. Practitioners caring about efficient model deployment might find this approach useful.
164 upvotes · 1 OCT 2026 · Xiangyu Zeng, Yuandong Yang, Zhiqiu Zhang et al.
This paper develops a unified model that combines perception, memory, and response for streaming video interaction, allowing for efficient and accurate processing of video content in real-time. Practitioners in the field of natural language processing and computer vision may care about this research as it aims to improve the performance of streaming video understanding models.
162 upvotes · 19 OCT 2026 · Xiaomin Yu, Hongliang Chen, Zhe Huang et al.
This paper evaluates the ability of Deep Search agents to conduct end-to-end research in real-world open Web environments, where they must autonomously search for, access, and integrate relevant evidence. Practitioners may care about this research to develop agents that can effectively search and retrieve information in complex, real-world settings.
158 upvotes · 30 JUL 2026 · Shuyao Shang, Yuqi Wang, Ruopeng Gao et al.
This paper introduces PhiZero, a world model that uses physical language to predict how the physical world evolves, allowing for more explicit reasoning and potentially more realistic simulations. Practitioners might care because this approach could lead to more realistic and interactive world modeling in applications like robotics, video games, and virtual reality.
158 upvotes · 14 AUG 2026 · Yijiang Li, Yijun Liang, Yunjie Tian et al.
This paper proposes a new method called Self-Supervised Visual On-Policy Distillation (S^2VOPD) that generates learning signals from asymmetric augmented views of images, allowing for effective on-policy learning without privileged information. Practitioners might care about this paper because it presents a simple yet effective way to improve performance on various perception benchmarks.
157 upvotes · 10 AUG 2026 · Mind Lab, Vin Bo, Asher Cai et al.
This paper introduces Macaron-V1, an open agent model family that enables continual learning and self-improvement in real-world environments, and explores its potential for collective intelligence. Practitioners might care about this work if they're interested in developing AI systems that can learn and adapt over time.
156 upvotes · 8 SEP 2026 · Ziyang Ma, Zhikang Niu, Wenming Tu et al.
This paper introduces AuK, an open-source model for speech generation and editing, which can perform a range of tasks with a single interface and achieves state-of-the-art performance on several tasks. Practitioners may care about this model for its potential to improve speech synthesis and editing capabilities in applications such as voice assistants and audio editing software.
155 upvotes · 18 AUG 2026 · Keyu Tu, Zhuowei Chen, Mengqi Huang et al.
This paper introduces a new benchmark for video generation tasks that require both achieving a desired outcome and maintaining semantic consistency with a reference image. Practitioners might care about this research because it can help evaluate and improve the performance of video generation models in real-world applications.
154 upvotes · 19 JUL 2026 · Yuhan Zhu, Changlian Ma, Xiangyu Zeng et al.
This paper develops a new approach to understanding videos by predicting when specific events or evidence occur within the video. Practitioners working on video analysis and AI models might care about this research because it could lead to more accurate and robust video understanding systems.
154 upvotes · 14 OCT 2026 · Panrong Tong, Quyu Kong, Pengxiang Li et al.
This paper introduces MAI-Gym, a platform for training and evaluating GUI agents in various environments, allowing for scalable reinforcement learning and enabling the creation of diverse and realistic tasks. Practitioners can use MAI-Gym to train agents that can perform well in both simulated and real-world environments.
153 upvotes · 6 OCT 2026 · Bingxi Hou, Guochao Jiang, Guofeng Quan et al.
This paper investigates how to improve the effectiveness of On-Policy Distillation, a technique that trains a student model on its own generated data with teacher feedback. By prioritizing supervision reliability over alignment coverage, the researchers found that using a smaller subset of shared vocabulary at aligned positions can lead to comparable accuracy to using the full shared vocabulary.
152 upvotes · 14 AUG 2026 · Zhiyuan Jiang, Fangrui Huang, Hanwen Xing et al.
This paper investigates how skills work in LLM agents, when they help, and why they fail, to improve their performance. Practitioners can benefit from understanding these factors to build more reliable self-evolving agents.
150 upvotes · 25 OCT 2026 · Xuan He, Sining Zhoubian, Ruozhen Yang et al.
This paper investigates the net value of agent memory in long-horizon agents, finding that dedicated memory systems often underperform without memory in many cases. Practitioners may care because understanding the net value of memory can help design more reliable and effective memory systems.
149 upvotes · 27 AUG 2026 · Tingyun Li, Wenfeng Feng, Weiqing Li et al.
This paper proposes a method to determine which past update evidence in a large language model is still relevant and useful after subsequent training, to prevent wasting compute and potentially degrading the model's performance. Practitioners in the field of autonomous systems and language models might care about this problem because it can lead to better model performance and efficiency in adapting to changing domains and requirements.
148 upvotes · 21 SEP 2026 · Peng Xia, Rujun Han, Zifeng Wang et al.
This paper introduces RRSI, a method to improve the performance of large language model (LLM) agents by iteratively editing their harness, which includes prompts and control flow, to achieve better performance on various tasks. Practitioners may care about this paper because it presents a way to regularize the self-improvement process of LLM agents to avoid overfitting.
148 upvotes · 23 OCT 2026 · Wendi Sang, Kai Li, Yifan Li et al.
This paper improves the efficiency of extracting the target speaker from audio-visual data in real-world acoustic scenes, which is crucial for applications like voice assistants. Practitioners may care about this research if they work on latency-sensitive voice recognition systems.
147 upvotes · 27 OCT 2026 · Hanqing Wang, Zhaotian Cai, Ruichuan An et al.
This paper introduces a new model called PDRVLA that helps robots understand the physical world from visual and language inputs, and generate actions accordingly. Practitioners in robotics and AI might care about this research because it aims to improve robots' ability to perform tasks in real-world environments.
146 upvotes · 17 SEP 2026 · DeepSeek-AI, Anyi Xu, B. Li et al.
This paper introduces DeepSeek-V4.1-Flash, a more efficient model that reduces the computational cost of long-horizon agents by optimizing its prefill process and cache compression. Practitioners can benefit from this model's improved performance and reduced storage needs for agentic workloads.
146 upvotes · 20 OCT 2026 · Pan Wang, Yihao Hu, Guangyuan Dong et al.
This paper proposes a new training method called Progress-Aligned Recurrence (PAR) to improve the performance of sequential state-tracking models on longer problems. By training the model to match the state after a certain number of operations and rescaling recurrent states, PAR enables models to generalize better to longer problems.
144 upvotes · 19 OCT 2026 · Zhiyu Li, Zeyu Zhang, Linyun Liu et al.
This paper introduces MemT-1.0, a new architecture that makes memory a part of foundation models, allowing them to accumulate and utilize information. Practitioners may care because this innovation can improve the efficiency and effectiveness of AI models in various tasks.
142 upvotes · 23 JUL 2026 · Shuqi Lu, Chaofan Li, Kun Luo et al.
This paper introduces AREX, a self-improving agent that recursively refines its answers by verifying intermediate results and using the partially verified state to guide subsequent refinement, aiming to improve the efficiency of deep research. Practitioners might care about AREX's approach to reducing the cost of discovery and verification in complex research tasks.
142 upvotes · 17 AUG 2026 · Yixuan Wang, Yifei Chen, Haichao Zhang et al.
This paper improves reinforcement learning for post-training language model reasoners by addressing two problems in existing methods: identical advantages for distinct reward profiles and fixed relative weights for all objectives. A new method, SA-MRPO, dynamically reallocates optimization effort toward under-optimized objectives while maintaining performance on well-satisfied objectives.
142 upvotes · 17 AUG 2026 · Xin Ding, Liang Mi, Mingzhe Huang et al.
This paper introduces Zetta, a system that enables embodied agents to learn and adapt in real-time while executing physical tasks, allowing for more efficient and effective learning. Practitioners in robotics and AI may care about Zetta's approach as it could lead to more reliable and scalable physical intelligence.
142 upvotes · 19 SEP 2026 · Hao Liang, Qihan Lin, Meiyi Qiang et al.
This paper develops a new type of AI model designed to help with teaching and learning in schools, and it shows that such models can be very effective at solving educational problems.
141 upvotes · 28 JUL 2026 · Simple AI, Yuteng Wei, Jinming Ma et al.
This paper develops a system that allows robots to learn manipulation policies using high-fidelity data without the need for real-robot teleoperation, which is expensive to scale. Practitioners can use this approach to train robots for tasks like precision insertion with high accuracy and success rates.
141 upvotes · 15 OCT 2026 · Yijiang Li, Bingyang Wang, Nuno Vasconcelos
This paper helps vision-language models (VLMs) think and explore in 3D space by interacting with the environment through actions and observations, rather than receiving pre-rendered images. Practitioners might care because it can improve the accuracy of VLMs on 3D benchmarks.
141 upvotes · 19 OCT 2026 · Tianqi Liu, Hanfei Zhao, Qifeng Liang et al.
This paper develops a world model that allows embodied agents to predict action consequences for both locomotion and manipulation across different robot and human embodiments. Practitioners might care about this research because it could lead to more sophisticated robots that can interact with their environment in a more human-like way.
138 upvotes · 27 AUG 2026 · Yuandong Pu, Le Zhuo, Sayak Paul et al.
This paper evaluates how well current video generation models can reproduce the distribution of possible behaviors under the same initial observation and action, and whether they can be improved to better align with real-world possibilities. Practitioners caring about realistic and diverse video content might be interested in the findings.