微信内可能无法直接打开本站。请点右上角 ··· → 在浏览器打开，或复制链接后用系统浏览器访问。
XMT
信流 · 上滑连读 · 来源可核
Lynk and Omnispace form Elveo Mobile to advance D2D services
Lynk Global has completed its merger with Omnispace and rebranded as Elveo Mobile, adding globally coordinated S-band spectrum to expand direct-to-device satellite services beyond basic messaging.…
- The post Lynk and Omnispace form Elveo Mobile to advance D2D services …
RSS 官方收录 · 可信分层展示
拒绝「差不多」，电商模型测评迎来「最严厉的父亲」
测评 AI 这件事，如今越来越难做了。几年前，AI 还是聊天机器人时，测评主要就是做题：写作的、数学的、编程的……最后形成一套跑分，用分数代表模型能力。但当 AI 从聊天框里走出来，变成能够调用工具、操作网页、处理文件、跨系统执行任务的 Agent，情况就变得复杂起来。…
- 平时我们看到的，是 AI 出现在手机上，能够刷淘宝、加购物车，最后下单。
- 实际上在商家的那一端，也有 AI 的参与，承担着比选购和下单更复杂的工作。
- 在专门考察电商环境中模型表现的 RealReplicaBench 测试中，经过 107 个真实商业任务的考核，所有参评模型都没有达到 60 …
RSS 官方收录 · 可信分层展示
Active Perception for Embodied Disambiguation
arXiv:2608.…
- 13605v1 Announce Type: new Abstract: Natural language provides robots …
- Existing interactive disambiguation methods primarily obtain additiona…
- We propose an active-perception framework for embodied target disambig…
RSS 官方收录 · 可信分层展示
Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents
arXiv:2608.…
- 13604v1 Announce Type: new Abstract: Detection of misunderstanding is …
- This shift cuts communicators off from the resources repair depends on…
- In this paper we analyse misunderstanding as a layered process in whic…
RSS 官方收录 · 可信分层展示
Measuring Cross-Task Behavioral Consistency in Language Model Agents
arXiv:2608.…
- 13598v1 Announce Type: new Abstract: Agent evaluation relies almost en…
- We argue that behavioral consistency across tasks is a distinct and me…
- BCM trains a model to predict task success from behavioral features of…
RSS 官方收录 · 可信分层展示
Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors
arXiv:2608.13591v1 Announce Type: new Abstract: High-confidence errors in large language models are often treated as evidence of fragile internal inference.…
- We study a different possibility: stable miscalibration, where a confi…
- We combine two diagnostics: a label-aware output-level audit score tha…
- On a multi-domain binary factual audit set, this audit score tracks wh…
RSS 官方收录 · 可信分层展示
Google Chrome is now available for Arm Linux. We tested it on a Raspberry Pi 5
Google Chrome web browser is now available for 64-bit Arm Linux, and we quickly tested it with Raspberry Pi OS on a Raspberry Pi 5GB 2GB SBC.…
- The open-source Google Chromium web browser has been available for Arm…
- Google wrote about working on a port last March, but hasn’t officially…
- However, users on Interfacing Linux have noticed that it can easily be…
RSS 官方收录 · 可信分层展示
Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents
arXiv:2608.…
- 13574v1 Announce Type: new Abstract: LLM agents increasingly operate a…
- These capabilities make agents useful, but they also introduce risks r…
- This paper presents Agentao, a governed local-first runtime for tool-u…
RSS 官方收录 · 可信分层展示
A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing
arXiv:2608.…
- 13573v1 Announce Type: new Abstract: Large Language Model (LLM) servin…
- However, existing LLM serving workload studies remain limited in scale…
- They often observe short time periods and provide limited visibility i…
RSS 官方收录 · 可信分层展示
Modular Cognitive Architecture Emerges in Large Language Models
arXiv:2608.…
- 13567v1 Announce Type: new Abstract: The human brain exhibits a striki…
- Is this modular organization a fundamental principle of how intelligen…
- Here, we test whether a similar organization emerges in Large Language…
RSS 官方收录 · 可信分层展示