每日AI论文

Jingwen Liang, Gengyu Wang
  • 0.0 (0)
  • Science
  • Updated Daily

每个工作日更新，解读 Hugging Face Daily Papers（https://huggingface.co/papers）中得票最高的论文。播客文稿和音频均由 AI 生成。欢迎反馈与建议！邮箱：dailypapercast.ai@gmail.com 创作者： Jingwen Liang，3D 机器学习，https://www.linkedin.com/in/jingwen-liang/ Gengyu Wang，LLM ML，http://wanggengyu.com 英文版收听： Spotify：https://open.spotify.com/show/21nrhmdaA8qoBiH8q03NXL Apple Podcasts：https://podcasts.apple.com/us/podcast/daily-paper-cast/id1777620236 封面图片：Kawen Kuang https://kawen.art

  1. 6d ago

    Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE

    🤗 Upvotes: 21 | cs.AI 作者: Ermo Hua, Xiangyu Hong, Baiting Wu, Che Jiang, Haozheng Hou, Yicheng Gu, Hanjing Wang, Qirui Zeng, Ming Zhang, Ning Ding, Qipeng Guo, Youbang Sun, Biqing Qi, Bowen Zhou 标题: Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE Arxiv: http://arxiv.org/abs/2610.27598v1 摘要: As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model scaling. However, mainstream models currently adopt hierarchical architectures, where experts in different layers, although topologically independent, exhibit substantial similarity and redundancy in their stored content. Compared to the hierarchically arranged \textbf{Local Expert} in existing mainstream models, we hypothesize that inter-layer shared \textbf{Meta Expert} hold greater potential. To this end, we conduct a multi-dimensional empirical comparison between Local and Meta Experts, and find that models incorporating Meta Experts exhibit lower parameter redundancy, together with lower cross-entropy loss and higher downstream task accuracy. With the activated quantity and the expert granularity held fixed, \textbf{our model matches the performance of Vanilla MoE using only 70--80\% of the experts}, substantially improving the model's scaling potential. Beyond removing inter-layer redundancy among experts and improving information storage efficiency, our theoretical analysis further shows that, compared with Local Experts, Meta Experts provide hidden states with more flexible residual pathways, thereby improving information retrieval efficiency.

  2. Oct 22

    Cache Engineering for Agents

    🤗 Upvotes: 55 | cs.CL 作者: Tianyu Fu, Ruoxi Wang, Zihan Min, Zhongqi Ren, Zhihao Li, Tengxuan Liu, Shengxu Mu, Hanling Zhang, Yu Wang 标题: Cache Engineering for Agents Arxiv: http://arxiv.org/abs/2610.28577v1 摘要: Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions. As these trajectories grow, key-value (KV) cache I/O and storage become the dominant cost. Trajectories can also exceed the LLM's maximum context length, requiring control over active cache growth. Prior work uses context engineering to reduce cache size by trimming or summarizing history. However, modifying the trajectory prefix invalidates subsequent cached states and triggers costly re-prefilling of retained context. Task accuracy can also suffer when too little context is retained to limit re-prefill costs. We propose cache engineering as a new scheme. It allows agents to directly control their active KV cache without modifying the trajectory or re-prefilling retained context. Specifically, agents can proactively use drop to exclude selected cache from future attention and repos to adjust retained keys' position encodings. We formalize these cache operations and identify history dependence as a serving challenge: identical token sequences can yield different cache states under different cache operation sequences, making prefix matching insufficient for correct cache reuse. Thus, we co-design the AKV serving engine. It provides a stateless interface compatible with existing serving APIs, while internally managing stateful cache reuse, eviction, and restoration. Experiments show that a tool-response rolling-drop cache policy improves average benchmark scores by 1.7 points and reduces average cost by 27.7%, compared with conventional threshold-triggered summarization. With AKV, it achieves up to 1.2x the output throughput and a 1.5x speedup in P95 request latency. Recursive self-improvement of cache policies further reduces cost by 7.1% over expert design. Our code is at https://github.com/thu-nics/AKV.

  3. Oct 22

    Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

    🤗 Upvotes: 53 | cs.AI, cs.CL, cs.LG 作者: Zhaoyang Wang, Qianhui Wu, Haorui Wang, Simon Yu, Baolin Peng, Canwen Xu, Hao Cheng, Wenlin Yao, Boyi Liu, Yite Wang, Jianfeng Gao, Huaxiu Yao 标题: Agent World Model in the Wild: Computer-Use Agent Environment Synthesis Arxiv: http://arxiv.org/abs/2610.26828v1 摘要: Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world computer systems is challenging and can introduce substantial security risks. We therefore propose Agent World Model in the Wild (WildAWM), a scalable pipeline for synthesizing controllable environments and tasks for training general computer-use agents (CUAs). Whereas existing approaches typically specialize in a single agent interaction interface, we construct executable environments that jointly support graphical user interfaces, model context protocol services, and command-line interfaces, allowing agents to flexibly combine visual interaction, tool use, and code execution. WildAWM is entirely powered by open-source models, demonstrating that high-quality computer-use environments can be generated without proprietary frontier models. Beyond environments, we address three recurring challenges in task synthesis: ensuring solvability, maintaining sufficient difficulty, and producing reliable verifiers, by introducing execution-based quality gates that combine heterogeneous agent rollouts, cross-judge consistency checks, and counterfactual probes of judgment robustness. The resulting pipeline synthesizes 341 long-horizon environment-task pairs that can require over 100 agent steps to solve and remain challenging even for frontier models, with GPT-6-Astra solving only 60% of them. We train two Qwen models of different sizes exclusively in these synthetic worlds. Both models achieve substantial gains across 8 out-of-distribution benchmarks spanning web, claw, and computer-use agents, demonstrating that learning in WildAWM's synthesized worlds generalizes broadly to unseen computer-use tasks. The code is publicly available at https://github.com/MSR-Orchard/WildAWM.

  4. Oct 22

    Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation

    🤗 Upvotes: 52 | cs.CV 作者: Ruopeng Gao, Yukun Huang, Jiarui Hu, Shuai Wang, Wenbo Hu, Ying Shan, Limin Wang 标题: Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation Arxiv: http://arxiv.org/abs/2610.29989v1 摘要: Autoregressive video diffusion models generate videos chunk by chunk, yet producing plausible continuations does not guarantee that they capture how scenes evolve. Under teacher forcing, strong temporal redundancy may allow local visual continuity to serve as a shortcut for current-chunk denoising, reducing the pressure to model visual evolution. We introduce Future Chunk Prediction (FCP), an auxiliary objective jointly optimized with teacher-forced denoising that predicts temporally separated chunks without access to the intervening visual context. Drawing supervision directly from training videos, FCP requires no additional pretrained visual encoder and leaves autoregressive inference unchanged. Our method achieves superior physical plausibility over standard teacher-forced autoregressive training with a lower overall training compute budget, highlighting the effectiveness and efficiency of future-chunk supervision for modeling visual evolution. Intriguingly, our visualizations suggest that FCP fosters a more structured representation space, which may be valuable for building autoregressive world models.

  5. Oct 22

    Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills

    🤗 Upvotes: 26 | cs.AI 作者: Letian Zhu, Han Li, Yifan Yao, Xinping Lei, Xinyu Che, Jiahao Wang, Dianyi Wang, Yucheng Fu, Jiakai Wang, Zhiqi Bai, Wenbo Su, Jiaheng Liu 标题: Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills Arxiv: http://arxiv.org/abs/2610.17860v1 摘要: Agent Skills improve LLM agents by making task knowledge reusable across sessions. Learning transferable Skills requires evidence about a procedure and its conditions of use, which a successful task attempt can leave untested. We introduce Socratic Skill Learning (SSL), which interleaves expert teaching with Student practice. An Educator guides investigation while the Student remains the sole environment operator and Skill author, able to question, test, and adapt advice. To test reuse beyond the learning task, we construct SkillTransferBench, with 35 task families and 408 executable cases, pairing public variation specifications with held-out evaluation in fresh solver sessions. On the main 22-family, 155-case cohort, Fixed-Window SSL reaches 0.801 utility, versus 0.723 without a Skill, 0.761 for adapted Trace2Skill (trajectory distillation), and 0.751 for adapted SKILL-KD (contrastive distillation). Across three model pairs on shared families, interleaved guidance outperforms expert authoring and post-hoc teaching. Process analysis links guidance to Student writing and package revision; a case study shows the Student testing and refining a proposed procedure for later reuse. As demand for new lessons falls, the cost of fixed-window review grows. Issue-Guided SSL tracks unresolved questions across Skill revisions to select and focus review, reaching 0.805 utility with 61.7% fewer Educator tokens and 16.9% fewer total acquisition tokens than Fixed-Window SSL on the main cohort.

  6. Oct 22

    Spectral-Spatial Interpretation

    🤗 Upvotes: 23 | cs.LG, cs.CV 作者: Haotian Ma, Ruqi Yang, Philip Townsend 标题: Spectral-Spatial Interpretation Arxiv: http://arxiv.org/abs/2610.21114v1 摘要: Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores. These separate views are limiting for multispectral data because channel relevance is often spatially localized and physically meaningful. We introduce Spectral-Spatial Interpretation (SSI), a full-grid attribution method over position-channel players (g,c). For each spatial position, SSI fixes the observed surrounding context, defines a conditional game over the channels at that position, and applies the Shapley value to this local game. The result is a full spectral-spatial attribution matrix rather than a single heatmap or a global channel ranking. SSI has a clear local interpretation. It satisfies Shapley fairness within each position, and aggregating its channel attributions exactly recovers the position-level contextual contrast obtained by replacing that position with the baseline. SSI also differs from context-averaged Owen-style hierarchical accounting, which uses the same position-channel grouping but averages over external spatial coalitions. On HLS Burn Scar, SSI outperforms an MC-Owen estimator across retained attribution metrics while using only about 6% of its evaluation budget. Across CUB-200, EuroSAT, and HLS Burn Scar under both per-channel mean and zero baselines, SSI achieves the best joint deletion and insertion AUC over dense, flat, and rank-1 baselines, yields the strongest spectral hit rates and channel deletion, and leads spatial localization on both annotated datasets. Code is available at https://github.com/AtheavenMa/Spectral-Spatial-Interpretation.

  7. Oct 22

    PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis

    🤗 Upvotes: 23 | cs.CL, cs.AI, cs.CV, cs.LG, cs.SE 作者: Qiushi Sun, Jingyang Gong, Yang Liu, Qiaosheng Chen, Zhangyue Yin, Zixian Huang, Hanxu Hu, Jing Xiong, Fangzhi Xu, Haochen Tan, Haoli Bai, Lifeng Shang, Xiaoguang Li, Ben Kao, Qipeng Guo, Lingpeng Kong, Jiahui Gao 标题: PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis Arxiv: http://arxiv.org/abs/2610.20538v1 摘要: Multimodal code intelligence connects the symbolic world of programs with the visual world their execution creates. Interest in this capability is burgeoning, as models are increasingly asked to produce charts, webpages, animations, and semi-structured documents. Recently, proprietary models have pushed far ahead, producing interactive artifacts even from a text description or a screenshot alone. Yet their data and training remain closed, and open progress is held back by the quantity and quality of available data and by the pipelines and methods for producing it. Quality is the harder of the two, since a sample must be correct as a program, well built, and above all visually right once rendered. No existing signal covers all three. Execution often returns just a pass or fail, code similarity does not map to the visual output, and task-specific verifiers do not generalize. To push open progress further, we start from the data side with PrismaForge, a hierarchical data pipeline centered on a synthesized rubric that decomposes these factors into checkable criteria. The same rubric serves as both filter and reward: it curates the supervised corpus, then drives reinforcement learning on visual-coding tasks. Leveraging PrismaForge for data synthesis and filtering, we build PrismaCoder-2M, the most diverse open dataset for multimodal code intelligence and the largest to date. On the model side, we train PrismaCoder-9B and PrismaCoder-35B on this data and release both. They lead the open state of the art by a wide margin and rival leading proprietary systems. Our analyses further show that the proposed rubric-based pipeline improves multimodal coding performance across model backbones. We release our code and data at https://qiushisun.github.io/PrismaCoder-Home/.

  8. Oct 21

    Focused Omni-Modal GUI Agents

    🤗 Upvotes: 97 | cs.CV 作者: Fuyao Zhang, Wenwen He, Jiaming Zhang, Yurong Hao, Xuan Wang, Guowei Guan, Che Wang, Longtao Huang, Wei Yang Bryan Lim 标题: Focused Omni-Modal GUI Agents Arxiv: http://arxiv.org/abs/2610.26203v1 摘要: Graphical User Interface (GUI) agents increasingly act over streaming omni-modal observations spanning screenshots, audio, video, interaction history, and device states. However, exposing this complete context uniformly at every step ignores that relevance is transient and sparse: the signal determining one action can become clutter at the next. Because executed actions feed back into the context, these errors compound into Sequential Distraction, driving the agent into irreversible trajectory drift. We formulate the underlying requirement as Focused Perception: a representation that is step-adaptive, action-sufficient, and non-intrusive. We realize this in FocusGUI, a lightweight adapter that dynamically prioritizes multimodal channels against a step-specific decision reference. Instead of uniformly processing all inputs, it compresses the most relevant evidence into a compact latent and subtly injects it into the frozen decoder's embeddings, guiding the model's attention without altering its native parameter space. FocusGUI trains from action supervision alone, requiring neither modality-relevance labels nor backbone fine-tuning. Across four omni-modal backbones, it raises overall Type Match by +33.2 and Exact Match by 3.0 times over the frozen backbone on average, and Type Match by +30.1 over the strongest existing enhancement method.

See All (262)

About

每个工作日更新，解读 Hugging Face Daily Papers（https://huggingface.co/papers）中得票最高的论文。播客文稿和音频均由 AI 生成。欢迎反馈与建议！邮箱：dailypapercast.ai@gmail.com 创作者： Jingwen Liang，3D 机器学习，https://www.linkedin.com/in/jingwen-liang/ Gengyu Wang，LLM ML，http://wanggengyu.com 英文版收听： Spotify：https://open.spotify.com/show/21nrhmdaA8qoBiH8q03NXL Apple Podcasts：https://podcasts.apple.com/us/podcast/daily-paper-cast/id1777620236 封面图片：Kawen Kuang https://kawen.art

Information

  • Creator
    Jingwen Liang, Gengyu Wang
  • Years Active
    2026
  • Episodes
    262
  • Rating
    Clean
  • Copyright
    © 2026 Jingwen Liang, Gengyu Wang