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
Conversation Coach: A Voice-enabled AI System that Helps Practice Difficult Workplace Conversations
arXiv:2609.…
- 00441v1 Announce Type: new Abstract: Effective manager-employee commun…
- Text-based chatbots offer a scalable approach but cannot provide reali…
- In this paper, we propose Conversation Coach, a voice-first AI system …
RSS 官方收录 · 可信分层展示
SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents
arXiv:2609.…
- 00434v1 Announce Type: new Abstract: Evaluating task-oriented dialogue…
- We propose SAGE (State-Grounded Abstention-Aware Evaluation), which co…
- Its recommended operating point, SAGE-Core, decides 81--91% of criteri…
RSS 官方收录 · 可信分层展示
SpecMind: Enabling Spectrum Intelligence via Multi-Agent Hybrid Retrieval-Augmented Generation
arXiv:2609.…
- 00427v1 Announce Type: new Abstract: The exponential growth of wireles…
- As a result, spectrum policymakers and engineers must process large vo…
- These data sources are often disaggregated and require significant tim…
RSS 官方收录 · 可信分层展示
Dependency-Aware Chain-of-Thought Compression for Financial Reasoning
arXiv:2609.…
- 00413v1 Announce Type: new Abstract: Chain of thought prompting improv…
- We present a Hierarchical Semantic Distillation Network, HSDN, for com…
- The framework combines semantic segmentation, dependency graph constru…
RSS 官方收录 · 可信分层展示
硬件加强版「WorkBuddy」，拿下数亿融资，瞄向你的终极上下文
作者｜苏子华 编辑｜靖宇 现场体验过 Violoop 之后，很多关于未来的「AI 助手」该长什么样、能做些什么、能力的极限究竟在哪的困惑，可能都会迎刃而解。因为 Violoop 已经把它们变成了现实。…
- Violoop 实物图｜图片来源：Violoop Violoop 是一款巴掌大小的硬件，即插即用，V4 版本通过一根 Type-C 线连在电…
- 它可以通过实时读取电脑屏幕上的全局信息，获得用户全部的上下文，实现主动式的 AI 助手。
- 极客公园获悉，Violoop 半年内完成了亿元级天使轮及 Pre-A 轮融资。
RSS 官方收录 · 可信分层展示
对话黄青虬：成立半年估值 70 亿，阿里腾讯联投，交出了能「长程执行」的第一个自研模型
作者｜苏子华 编辑｜靖宇 机器人行业现在最关心的一个问题：它能干完一整件事吗？几十秒的抓取物品的视频已经撑不起估值了。把一件事从头干到尾，成了最新的考题，行业里叫它「长程任务」。8 月 19 日，世界机器人大会，一台机器人首次亮相，用 15 分钟回答了这道题：收拾客厅，检查冰箱，把烘干机里的衣服拿出来，放进新的一批，按下启动键，最后把衣服叠好。…
- 里面大概有七八十个动作，自主完成，全程没掉链子。
- 正在忙活衣物烘洗家务的 MORPHI KINO 机器人｜图片来源：MORPHI 造它的公司叫墨奇（MORPHI），成立刚 8 个月。
- 联合创始人黄青虬出生于 1994 年，清华自动化本科、香港中文大学 MMLab 博士。
RSS 官方收录 · 可信分层展示
RestoreBench: Can AI Agents Restore Power Flow Convergence?
arXiv:2609.…
- 00384v1 Announce Type: new Abstract: Large Language Model (LLM) agents…
- Diagnosing and resolving non-convergent power flow cases is a promisin…
- We introduce a benchmark that evaluates these capabilities across mult…
RSS 官方收录 · 可信分层展示
Dr. Claw: An AI Scientist Workspace for Vibe Research
arXiv:2609.00365v1 Announce Type: new Abstract: Command-line coding agents (e.g.…
- , Claude Code, Gemini CLI) can already read and write files and sustai…
- We present Dr.
- Claw, an open-source workspace that wraps existing coding-agent execut…
RSS 官方收录 · 可信分层展示
A Stable Aggregation Method for Quantum Federated Learning
arXiv:2609.00356v1 Announce Type: new Abstract: Quantum federated learning (QFL) enables clients to train quantum neural network (QNN) models without sharing private data.…
- We find that aggregation in QFL is unstable under heterogeneous data, …
- Moreover, QFL is non-trivially challenging because several QNN paramet…
- We develop a novel self-consistent midpoint aggregation method for sta…
RSS 官方收录 · 可信分层展示
Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models
arXiv:2609.…
- 00355v1 Announce Type: new Abstract: Speculative decoding accelerates …
- The drafter stays autoregressive, so it must stay small.
- A small drafter cannot afford the image at every step, so vision is co…
RSS 官方收录 · 可信分层展示
SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning
arXiv:2609.…
- 00342v1 Announce Type: new Abstract: Whole-slide images (WSIs) are cha…
- Existing WSI models and pathology agents can aggregate slide features …
- We introduce SlideBank, a training-free framework that represents each…
RSS 官方收录 · 可信分层展示
Human-AI Co-Interpretation for Responsible AI: A Hermeneutic Perspective
arXiv:2609.…
- 00334v1 Announce Type: new Abstract: Across law, education, policy ana…
- Yet a recurrent failure mode -- what I call \textit{interpretive mispl…
- In such settings, the risk is not only factual error but lost accounta…
RSS 官方收录 · 可信分层展示
The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systems
arXiv:2609.…
- 00275v1 Announce Type: new Abstract: Fleets of LLM agents now external…
- Current controls check one effect at a time, so a fleet of individuall…
- We propose the irreversibility budget, a cumulative account of residua…
RSS 官方收录 · 可信分层展示
Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching
arXiv:2609.…
- 00274v1 Announce Type: new Abstract: Two-sided service marketplaces ar…
- Relying on inferred intent rather than fixed-form fields forces these …
- We present an autoresearch loop that generates this taxonomy, one occu…
RSS 官方收录 · 可信分层展示
The Answer Is Not the Argument
arXiv:2609.00264v1 Announce Type: new Abstract: Chain-of-thought monitoring is proposed for AI oversight, yet evaluations often provide monitors with a trusted reference answer.…
- We ask whether answer access improves reasoning verification or mainly…
- We collected 237 step-numbered solutions to 79 Humanity's Last Exam ph…
- The reference standard combined physicist annotations, an independent …
RSS 官方收录 · 可信分层展示
IFA 2026：添可诠释智能清洁的未来图景
“添可洗地机，定义每一代“不只是一句口号，更代表着添可不断突破创新、让生活更简单的长期承诺。作为智能洗地机品类开创者，添可将再次亮相2026年9月4日至8日举办的德国柏林国际消费电子展（IFA）——这是欧洲规模最大的消费电子与家电行业盛会。…
- 届时，添可将带来覆盖多个家居清洁品类的全新产品，进一步展现其推动智能清洁标准不断升级的决心。
- 自净即是未来：添可眼中的明日清洁愿景本届IFA上，添可带来了全新传播主题“The Future Cleans Itself”（自净即是未来）。
- 在这一主题下，添可描绘了一个更智能、更自动、也更简单的清洁未来。
RSS 官方收录 · 可信分层展示
Hypotheses-Guided Self Distillation for Continual Personalization
arXiv:2609.…
- 00251v1 Announce Type: new Abstract: As people increasingly interact w…
- However, user preferences are rarely stated in full, and instead emerg…
- We introduce HypReflect, a reliable, scalable framework for continual …
RSS 官方收录 · 可信分层展示
Authority Bias in Conversational Search Engines for Academic Paper Recommendation
arXiv:2609.…
- 00248v1 Announce Type: new Abstract: Large Language Models (LLMs) are …
- We investigate authority bias: systematic preference for papers based …
- Holding title and abstract constant, we vary authority metadata across…
RSS 官方收录 · 可信分层展示
Invalidation Contracts for Cross-Episode Agent Memory
arXiv:2609.…
- 00243v1 Announce Type: new Abstract: LLM agents that cache recovery su…
- Server-side data drift turns those cached fixes into silent failures, …
- We introduce invalidation contracts, a protocol layer that attaches ve…
RSS 官方收录 · 可信分层展示