项目频道 - GAP x Hailey Bieber：欢迎来到1996

视频今年 7 月，GAP 携手全球时尚偶像海莉·比伯（Hailey Bieber），共同推出了名为“The Hailey Jean”的限量牛仔胶囊系列。这一系列在 7 月 17 日发售后，短短几分钟内便在全球各大渠道宣告售罄，更在社交媒体上掀起了一场“海莉神裤”的热潮。…

• 这次合作的起点，被定格在了 “1996”。
• 为了还原那种纯粹的复古质感，GAP 组建了一支顶级的视觉团队。
• 广告大片由时尚摄影大师 Mario Sorrenti 掌镜，造型则出自顶级形象顾问 Alastair McKimm 之手。

RSS 官方收录 · 可信分层展示

Alienware's new 25-inch 560Hz gaming monitor is its fastest ever

Alienware's new 25-inch 560Hz gaming monitor is its fastest ever.

RSS 官方收录 · 可信分层展示

Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems

arXiv:2609.…

• 02264v1 Announce Type: new Abstract: Adapting the communication topolo…
• We argue that this formulation is misaligned with the problem.
• Empirically, topologies that survive a reward filter collapse to about…

RSS 官方收录 · 可信分层展示

APEx: Distillation of Agent Procedural Experience for Adaptive Deep Research Question Answering

arXiv:2609.…

• 02253v1 Announce Type: new Abstract: Deep research agents augment larg…
• Learning from prior experience is crucial for continual improvement, y…
• We propose APEx, a hierarchical experience utilization framework that …

RSS 官方收录 · 可信分层展示

LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails

arXiv:2609.02246v1 Announce Type: new Abstract: Self-improving agent pipelines have a problem at their center.…

• An optimizer rewrites prompts to score higher, and the score comes fro…
• That judge has the last word on whether the system is getting better, …
• The judge should be demoted from oracle to advisor: its verdict become…

RSS 官方收录 · 可信分层展示

Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training

arXiv:2609.02244v1 Announce Type: new Abstract: Large language models (LLMs) often struggle when low-resource training data are ambiguous or incomplete.…

• Task-level natural-language priors can provide useful guidance in such…
• We propose Prior-Guided Tuning (PGT), a training perspective that inco…
• Under this perspective, we introduce Contrastive Prior Steering (CPS),…

RSS 官方收录 · 可信分层展示

Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality

arXiv:2609.02242v1 Announce Type: new Abstract: AI assistants often collaborate by proposing candidate edits, plans, or designs that users evaluate before adoption.…

• Existing assistance methods focus on proposal quality or user-goal inf…
• We study evaluability-aware proposal planning, where proposals serve b…
• We formalise this setting as ProSE, a hidden-parameter sequential assi…

RSS 官方收录 · 可信分层展示

Artek’s Stool 60 Receives Handcrafted Leather “Shoes” From Hender Scheme

SummaryHender Scheme and Artek introduce raw leather "shoes" for Alvar Aalto’s Stool 60 legs.…

• The capsule includes leather-wrapped trays, baskets, and custom furnit…
• Releasing October 10 at Sukima, Artek Tokyo, Artek Helsinki and select…
• Japanese leather artisan brand Hender Scheme has partnered with renown…

RSS 官方收录 · 可信分层展示

A$AP Rocky Created a Maximalist Man City Jersey for His Manchester Concert This Weekend

Fans can also buy Man City's home, away and third kits with custom A$AP nameplates.

RSS 官方收录 · 可信分层展示

PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks

arXiv:2609.…

• 02236v1 Announce Type: new Abstract: Group-based reinforcement learnin…
• To obtain more fine-grained credit assignment, recent work such as GiG…
• However, these step-level signals still rely on the final outcome of e…

RSS 官方收录 · 可信分层展示

PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessment

arXiv:2609.…

• 02231v1 Announce Type: new Abstract: Interview assessment requires per…
• We introduce PhoenixNest-Video, an evidence-grounded multimodal agent …
• It builds a semantic video graph as structured working memory, perform…

RSS 官方收录 · 可信分层展示

SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams

arXiv:2609.…

• 02217v1 Announce Type: new Abstract: LLM agents increasingly self-impr…
• On long-horizon workloads where each task demands a different solution…
• We argue the missing unit of reuse is the solving procedure shared by …

RSS 官方收录 · 可信分层展示

PEARL: Path-Entity Aligned Relational Learning with Contextual Subgraphs for Inductive Knowledge Graph Completion

arXiv:2609.…

• 02216v1 Announce Type: new Abstract: Inductive knowledge graph complet…
• Existing subgraph- and path-based approaches often encode relational p…
• We propose PEARL, a Path-Entity Aligned Relational Learning framework …

RSS 官方收录 · 可信分层展示

ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models

arXiv:2609.…

• 02215v1 Announce Type: new Abstract: Safety alignment trains large lan…
• Requests that only recontextualise the same operational content, chang…
• The ASCII Attack is one such recontextualisation.

RSS 官方收录 · 可信分层展示

项目频道 - 新西兰电信广告：表情包聊不明白的，还是电话聊吧

谁还没吃过线上聊天词不达意的苦啊。对面发过来一个赞，你当人家认可的“你很好”，事实是恨上了的“你好得很”；而你发出去一个“hh”，你想说的是“哈哈”，对面却可能以为是“呵呵”……这哪里是聊天，分明是网络用语十级测试选择题。…

• 新西兰电信运营商One New Zealand，就从这些线上聊天常见的沟通障碍出发，推出一系列户外广告，请路人一起猜猜，那些聊天框里丢出的e…
• You've offended me deeply: I will be thinking about this at 3am.
• And so will you.

RSS 官方收录 · 可信分层展示

Home Chef Promo Codes for September 2026

Enjoy up to 50% off deliveries, free meals, and more with the latest Home Chef coupons.

RSS 官方收录 · 可信分层展示

ExpressVPN Coupons: 73% Off

Learn how to get the best value from your ExpressVPN subscription plans, whether you need a flexible 1-month plan or want to lock in up to 61% savings on multi-year deals.

RSS 官方收录 · 可信分层展示

The 2026 El Niño Is Being ‘Supersized’ as Impacts Worsen

The World Meteorological Organization is warning that the climate phenomenon that has the Pacific running a fever will last until at least February, with dire consequences for weather worldwide.

RSS 官方收录 · 可信分层展示

Diagrid Catalyst 2.0 发布，为 AI 智能体新增持久化、可验证的执行能力

点击查看原文>

RSS 官方收录 · 可信分层展示

成立不到一年连融三轮，专治失眠的 AI 床头灯「火」了

头图来源：Fullive.ai 一家成立几个月、第一款产品即将量产的 AI 硬件公司，已经连续融了三轮：高瓴连续三轮加注，智元机器人等机构先后进入股东名单；到了今年 7 月，招商局创投又领投了它的新一轮融资。…

• 这家公司叫 Fullive.
• ai，创始人郑昊本科就读于清华数学系，此后一路跨过生物统计、因果推断、AI、医学和硬科技投资；联合创始人韦骁龙来自北大计算机，此前曾在华为、…
• 团队里还有参与过华为手环、WHOOP 等穿戴设备的硬件人员，以及来自百度、大疆等公司的算法和商业化老兵。

RSS 官方收录 · 可信分层展示

Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning

arXiv:2609.02191v1 Announce Type: new Abstract: Human interventions at fault points can alter the diagnostic accuracy of multi-agent medical systems.…

• We defined fault points as moments in AI agent conversations, in which…
• Using the MedQA dataset, this study analyzed simulated doctor-patient …
• Correct intervention methods showed an improvement in baseline diagnos…

RSS 官方收录 · 可信分层展示

EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision

arXiv:2609.…

• 02133v1 Announce Type: new Abstract: Empathetic response generation re…
• We formulate this as response-side affective-orientation control and u…
• We construct EmojiDialogue, an utterance-level extension of Empathetic…

RSS 官方收录 · 可信分层展示

FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs

arXiv:2609.02168v1 Announce Type: new Abstract: Fragmented safety evaluation undermines the governance of dangerous AI capabilities.…

• We present a modular framework that evaluates each model through three…
• Pluggable modules supply scenario seeds, knowledge banks, hazard queri…
• Instantiating the framework with a chemical-biological (CB) module, we…

RSS 官方收录 · 可信分层展示

Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents

arXiv:2609.…

• 02129v1 Announce Type: new Abstract: Data-centric agents repeatedly pe…
• Yet successful discovery outcomes are typically discarded rather than …
• We introduce persistent discovery context, a lightweight memory layer …

RSS 官方收录 · 可信分层展示