arXiv:2610.38100v1 Announce Type: new Abstract: Large language models (LLMs) appear to represent and reason about a large range of phenomena. In particular, recent studies have examined whether LLMs can accurately reason about causation. One of the most commonly used benchmarks for evaluating formal causal reasoning in LLMs is CLadder, a framework for procedural generation of benchmark data sets that was released in 2023. Experiments with CLadder appear to indicate that LLMs can perform formal c
arXiv:2610.38101v1 Announce Type: new Abstract: In recent years, warehouse logistics optimization has increasingly focused on intelligent, data-driven systems to enhance operational efficiency. Conventional static product placement strategies are being progressively replaced by dynamic slotting approaches that can adapt to real-time variations in warehouse conditions. In this work, we present a novel framework that employs a reinforcement learning agent integrated within a FlexSim-based Digital
arXiv:2610.38117v1 Announce Type: new Abstract: Effective firefighter training requires practice under dynamic and stressful emergency conditions, yet real-world live-fire exercises are costly, risky, and difficult to scale. Virtual Reality (VR) offers a safe and controllable alternative, but many existing VR firefighter training systems rely on fixed scenarios or provide limited difficulty adaptation, making it difficult to maintain an appropriate level of challenge for skill development as tra
arXiv:2610.38120v1 Announce Type: new Abstract: Large Language Models (LLMs) treat all context tokens uniformly, lacking explicit separation between executable instructions and passive data. This leads to prompt injection vulnerabilities, ambiguous instruction binding, and unreliable execution control. We present a post-training methodology using LLMON (LLM Object Notation), a framework that enables separating instructions from data and requires explicit identifier-based execution. We construct
arXiv:2610.38144v1 Announce Type: new Abstract: A recurring design choice in building AI systems is whether, when a task is too hard for a model, to expand the model (make it larger, better-prompted, fine-tuned), or to decompose the task (extract the parts that admit a deterministic solution to a host, leaving the model only the irreducibly fuzzy residue). We make three claims. First, that many tasks commonly delegated whole to a model are in fact deterministic tasks with a small generative core
arXiv:2610.38147v1 Announce Type: new Abstract: Agent skills package instructions, scripts, and resources for specialized tasks and are increasingly distributed through public Web repositories. However, existing skill benchmarks primarily focus on downstream task execution, insufficiently assessing specification quality, behavioral robustness, semantic alignment, and responsibility boundaries. Their reliance on task-specific tools, environments, and repeated executions limits scalability and pre
我即将关停我的小项目： https://xaisite.com/cn/pages/shutdown 内心还是有太多波澜。最近 1 年，真的深深感受到什么叫“时代的车轮碾过去连声招呼都不打”。 很多时候自己熬夜做个功能或者小工具，结果底层大模型随手搞个更新，或者上游一变动，之前的努力直接就被降维打击了。这种无奈感，估计做独立开发或者跟 AI 打交道的 V 友懂的都懂。 但另一方面，说实话又很难不兴奋。以前一个人根本不可能搞定的大工程，现在靠 AI 助手居然真能折腾出来，每天看着新东西出来，心里还是挺燃的。 就是这种既怕跟不上被淘汰，又忍不住想卷进去的感觉，真的挺矛盾挺难受的。 大家最近在搞 AI 相关的东西时，会有这种感觉吗？平时都是怎么调整心态的？
我做了个安卓原生 IM ，叫 Ball ，现在在 Google Play 内部测试阶段，还差几个人。 你需要：一台 Android 手机，加一个能上 Google Play 的 Google 账号。 你要做的：留一个 Google 邮箱（评论里不方便就发 summer@stags.cn ），我加进测试名单，你点链接装上，用两天告诉我哪里别扭。 关于这个 App：注册只要用户名和密码，不需要手机号；没有广告，也没有推荐流，就两个页面，会话列表和聊天。 内测链接： https://play.google.com/apps/internaltest/4700940105209393779 任何反馈都欢迎，尤其是「用起来别扭但说不上为什么」那种。
开发者一枚，目前在加拿大 Calgary 创业，最近正在筹备一个面向开发者的 Mac mini 实体主机托管服务。 主要考虑到部分开发者有长期运行 macOS 环境、远程开发、自动化任务以及 AI Agent 的需求，但自己购买和维护设备，或者寻找合适的海外部署环境，可能不太方便。 我们计划提供的是实体 Mac mini 托管，而不是普通的共享 VPS 。 几个特点： 加拿大 Calgary 本地部署 ，计划使用当地住宅网络环境。 专属实体设备 ，每台 Mac mini 独立使用，不是共享虚拟机。 面向长期运行需求 ，例如远程开发、自动化任务、AI Agent 等。 支持自有设备托管 ，也计划提供包含实体设备的托管方案。 目前项目还在筹备阶段，尚未正式开放服务。 想先了解一下 V 友们是否有这方面的需求，以及大家更关注哪些问题，比如网络、远程访问、设备配置、稳定性或者托管成本。 有兴趣的朋友可以在评论区留言或者私信我，我会单独发送项目介绍和初步方案。 也欢迎有相关经验的朋友交流建议。