All published intelligence, sovereign stack research, ecosystem news, and AI foundation model reviews.
arXiv:2610.31918v1 Announce Type: new Abstract: Distilling interactive LLM agents requires choosing between teacher-generated demonstrations and student-generated experience, corresponding broadly to off-policy and on-policy distillation. While both have proven effective, we…
arXiv:2610.31972v1 Announce Type: new Abstract: Evaluating conversational agents that act on live, mutable enterprise data is hard: replayed sessions drift as backend state changes, and a benchmark built today can silently go stale as the data it describes moves on. We present…
arXiv:2610.31985v1 Announce Type: new Abstract: LLM agents are increasingly deployed in collaborative settings where they pursue separate tasks while sharing resources and operating under review or oversight processes. Such settings create safety risks not only when agents are…
arXiv:2610.32022v1 Announce Type: new Abstract: Intent recognition in human-robot interaction requires agents to resolve ambiguous natural language instructions by inferring the speaker's underlying goals. Research has increasingly focused on two notable paradigms for addressing…
arXiv:2610.32024v1 Announce Type: new Abstract: Task instructions from users for agents are inherently underspecified, especially regarding safety boundaries--creating behavioral risks. To study these risks, we introduce BARC-Bench, a collection of 110 tasks across nine…
arXiv:2610.32026v1 Announce Type: new Abstract: Conventional neural-network training typically follows a predefined optimization recipe, motivating a LLM agent that monitors training dynamics and adjusts optimizer settings as training progresses, but a fixed agent policy does…
arXiv:2610.32034v1 Announce Type: new Abstract: The growing population of orbital debris has intensified interest in active debris removal and on-orbit servicing, for which dual-arm space manipulators offer improved grasping stability and load distribution relative to single-arm…
arXiv:2610.32045v1 Announce Type: new Abstract: AI-for-Science agents are increasingly being used for formulating scientific hypotheses, running autonomous experiments, and interpreting evidence. These agents are constructed by integrating a large language model (LLM) into a…
arXiv:2610.32046v1 Announce Type: new Abstract: Recent \emph{test-time training} (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scientific discovery tasks. However, TTT introduces…
arXiv:2610.32057v1 Announce Type: new Abstract: We present HyScale, a long-context training system for learned sparse attention. Learned sparse attention is a promising architecture for million-token contexts, widely adopted in production since DeepSeek-V3.2. Selection, however,…
arXiv:2610.32060v1 Announce Type: new Abstract: Multi-agent LLM systems aim to improve reasoning through debate, evidence sharing, and mutual correction, but interaction can also introduce failures that final accuracy alone cannot explain. Agents may converge too early, ignore…
arXiv:2610.32096v1 Announce Type: new Abstract: Diffusion language models (DLMs) support bidirectional denoising and iterative refinement, but generation remains largely controlled by token-level masking schedules. This leaves draft-level refinement implicit and limits explicit…
arXiv:2610.32069v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) can perceive a traffic scene, reason about it, and propose a driving action within a single model. However, existing MLLM-based drivers reason from scratch at each frame and commit to…
arXiv:2610.32087v1 Announce Type: new Abstract: Understanding language-agent behaviour requires learning how actions are organised across a trajectory and how this organisation relates to context and outcomes. We propose a general framework that connects data-driven behavioural…
arXiv:2610.32099v1 Announce Type: new Abstract: Fixed source superposition and frequency partitioning constrain how communication content interacts with a probing reference in integrated sensing and communication (ISAC). We learn nonlinear waveform fusion across scales for image…
arXiv:2610.31937v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) remain vulnerable to carefully orchestrated multi-turn interactions that progressively bypass safety mechanisms. However, many existing red-teaming approaches rely on heuristics or impose strong…
arXiv:2610.31971v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly participate in negotiations on behalf of individuals and organizations, yet they remain vulnerable to manipulation, particularly in repeated multi-party interactions. Classical…
Together AI 与 Y Combinator 为 YC 初创企业推出首个 GPU 集群
所以你写了这一行。您从张量中取出一个数字。也许是为了根据阈值检查它。也许只是为了打印它。感觉很自由，不是吗？事实并非如此。在已编译的模型上，这一行对您做了两件完全不同的事情。几乎每个人都有他们的模型......
The footage looks okay, as long as you're not seeking artistry, inspiration, or human interest.
Claude can now edit your videos. You upload the raw footage, and you get a Reel with subtitles, graphics, and sound. But it's better to break the task into five stages and go through them in one chat. For this type of editing, you need Claude's code with a tool like Hyperframes.…
The restaurant's AI-powered camera displays empty tables and counts how long guests have been seated at others. Once a guest is seated, the table on the panel turns red, and the timer starts. When the table is empty, it turns green again after a short pause. The manager sees the…
猫王埃尔维斯·普雷斯利音乐目录的所有者起诉 Anthropic 公司，指控其未经许可使用 274 首歌曲训练其 AI 模型。这起诉讼对 AI 开发者构成了来自艺人继承人的重大法律挑战，……
事实证明，人工智能代理的四分之一技能都是不安全的 - NVIDIA 推出了一个工具来检查它们。 NVIDIA 发布了免费的 SkillSpector 扫描仪，可分析增强 AI 代理能力的技能。这些技能使神经网络...
GitHub 上已收集了 700 多个使用 Claude 创建视频的提示。现在，您只需用普通语言描述所需的结果即可创建动画、动态图形、3D 场景甚至交互式迷你游戏。该集合包含 700 多个现成的示例。每一个…
Компания Джека Дорси Block только что выпустила ИИ-голос, который совершенно невозможно отличить от живого человека. Он называется Dessa. Он смеется посреди фразы так, как это сделал бы ваш друг. Он говорит: «Ага». и « Понял». прямо во время вашей речи. Он делает паузы,…
过去一周的结果才是最重要的 2027 年人工智能公司业务趋势。代理商务的未来。人工智能代理的支付：现在的斗争是什么？分析到这里。人工智能代理的新金融基础设施。人工智能代理的隐性税收——谁将从中赚钱？分析到这里...
科学文章太长，所以我只想请AI转述一下。 But there is a fear that he will miss important mathematical calculations and conditions. And if you need to return to the original, you will have to look for the desired section again. TextFold 的开发人员已经创建了相当......